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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5856
    Prev
    Next
    INDEX
    Explanations

    voice and face

    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
     observing
    -0.09
     Towards
    -0.07
    八个
    -0.07
     actors
    -0.07
     fourteen
    -0.07
     yp
    -0.07
    leine
    -0.07
    找出
    -0.07
    上升
    -0.07
    .deploy
    -0.07
    POSITIVE LOGITS
    的衣服
    0.07
    ];
    ↵
    0.07
    つか
    0.06
    крут
    0.06
    건축
    0.06
    的风险
    0.06
    "]],↵
    0.06
    怎么会
    0.06
     Brick
    0.06
     Granted
    0.06
    Activations Density 0.211%

    No Known Activations