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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107891
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nest
    -0.28
     nests
    -0.28
    ç¨ĭ
    -0.27
    Ĭ¶
    -0.27
    大æ°Ķ
    -0.26
    æ¦ĤåĨµ
    -0.25
     stressed
    -0.25
    ctp
    -0.25
    roe
    -0.24
     nale
    -0.24
    POSITIVE LOGITS
    antly
    0.26
    }}},↵
    0.25
     Tone
    0.25
    }}],↵
    0.24
    ,},↵
    0.24
    esktop
    0.23
     lòng
    0.23
    æĸ°éĹ»ç½ij
    0.23
    bson
    0.23
     Histor
    0.23
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.