© 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 EvalsExportsinterp-engineNEWAPI 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. 30092
    Prev
    Next
    INDEX
    Explanations

    privilege

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of privilege-related concepts—words and phrases indicating privileges, privileged access, or privilege escalation.

    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
     Blast
    -0.07
     AudioSource
    -0.07
     каждой
    -0.07
     תא
    -0.07
     Nicole
    -0.07
    ุม
    -0.07
    Tour
    -0.07
    <*
    -0.07
    تجنب
    -0.07
    jom
    -0.07
    POSITIVE LOGITS
     privileges
    0.08
     advant
    0.07
    ||||
    0.07
    rparr
    0.07
    .pageSize
    0.07
    .Excel
    0.07
    ᄇ
    0.07
    儡
    0.07
    학생
    0.07
     tranqu
    0.07
    Activations Density 0.005%

    No Known Activations