© 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. 11-RESID-POST-AA
    6. 92878
    Prev
    Next
    INDEX
    Explanations

    ig

    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
    㘎
    -0.07
     Must
    -0.07
    emo
    -0.07
    ʯ
    -0.07
    设想
    -0.07
    ᆱ
    -0.07
     다양한
    -0.07
     Monte
    -0.07
     abuse
    -0.07
    عكس
    -0.06
    POSITIVE LOGITS
    回到了
    0.07
    >//
    0.07
     stairs
    0.07
    压迫
    0.06
     "="
    0.06
    _GAME
    0.06
    ôm
    0.06
    人民服务
    0.06
    -values
    0.06
     pointing
    0.06
    Activations Density 0.002%

    No Known Activations