© 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. 122208
    Prev
    Next
    INDEX
    Explanations

    abuse

    np_max-act · gemini-2.0-flash

    This neuron detects passages describing abuse or domestic violence and their impact on victims.

    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
    -pl
    -0.07
    回去
    -0.07
    测
    -0.07
     Seamless
    -0.07
    採
    -0.07
    ">//
    -0.07
    を取り
    -0.07
    bench
    -0.07
    啷
    -0.07
    猄
    -0.07
    POSITIVE LOGITS
    stype
    0.07
     gusta
    0.07
     FDA
    0.07
     Aging
    0.07
     אזרחי
    0.07
    cea
    0.07
    sizes
    0.07
    Ô
    0.07
    asename
    0.06
    É
    0.06
    Activations Density 0.117%

    No Known Activations