© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 83523
    Prev
    Next
    INDEX
    Explanations

    authentication tokens and passwords

    np_max-act · gemini-2.0-flash

    the neuron detects mentions of authentication/identity verification or other security-sensitive verification steps.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blinking
    -0.07
    툭
    -0.07
     street
    -0.07
    放手
    -0.07
    高地
    -0.07
    /windows
    -0.07
     Fn
    -0.07
     overweight
    -0.07
     software
    -0.06
     NSStringFromClass
    -0.06
    POSITIVE LOGITS
     filtr
    0.07
     форм
    0.07
    Known
    0.07
    	Add
    0.07
     María
    0.07
    STIT
    0.07
    $result
    0.06
     sculpt
    0.06
    ueue
    0.06
    Jul
    0.06
    Activations Density 0.089%

    No Known Activations