© 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. 11-RESID-POST-AA
    6. 92178
    Prev
    Next
    INDEX
    Explanations

    medical complications/infections

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pil
    -0.08
    垱
    -0.07
    停车
    -0.07
    鳏
    -0.07
    offline
    -0.07
    _mouse
    -0.07
    tokenizer
    -0.07
     valeur
    -0.06
    ﯕ
    -0.06
    hotel
    -0.06
    POSITIVE LOGITS
    श
    0.08
    手持
    0.08
     __________________
    0.08
     //////////////////////////////////
    0.07
     Brown
    0.07
    Brown
    0.07
    മ
    0.07
     Rocket
    0.07
    DTD
    0.07
    他说
    0.07
    Activations Density 0.001%

    No Known Activations