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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 68479
    Prev
    Next
    INDEX
    Explanations

    say the ending -force

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʋ
    -0.07
    udden
    -0.07
    女士
    -0.07
    ocos
    -0.06
    ************************
    -0.06
    vere
    -0.06
    是多少
    -0.06
    眼睛
    -0.06
     Four
    -0.06
    ulous
    -0.06
    POSITIVE LOGITS
     triang
    0.07
    ="/"
    0.07
    影响力的
    0.07
    friendly
    0.07
    /data
    0.07
    .hide
    0.07
    Manual
    0.06
    configure
    0.06
     menacing
    0.06
    路线
    0.06
    Activations Density 0.033%

    No Known Activations