Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ʇ
    -0.07
    (sin
    -0.07
     selves
    -0.07
    acias
    -0.07
     eof
    -0.07
    Ts
    -0.07
    舒服
    -0.07
    当地时间
    -0.07
    🙃
    -0.07
    着手
    -0.07
    POSITIVE LOGITS
    -build
    0.07
    _AND
    0.07
    _write
    0.07
    שיווק
    0.07
    _ord
    0.07
    הקמת
    0.07
    _media
    0.07
    Published
    0.07
    뺘
    0.07
    annt
    0.06
    Activations Density 0.000%

    No Known Activations