© 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. 7-RESID-POST-AA
    6. 76224
    Prev
    Next
    INDEX
    Explanations

    priest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ても
    -0.07
    是真的
    -0.07
    uely
    -0.07
     {\↵
    -0.07
    とはい
    -0.07
    זרח
    -0.07
    來自
    -0.07
     реально
    -0.06
    アルバ
    -0.06
     ancestry
    -0.06
    POSITIVE LOGITS
    @
    0.07
     minute
    0.07
     Lounge
    0.07
     legion
    0.07
    ":[{↵
    0.07
    QUIT
    0.06
    .commons
    0.06
     $
    0.06
    [])↵
    0.06
     lab
    0.06
    Activations Density 0.003%

    No Known Activations