© 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. 31-TRANSCODER-HP
    7. 18732
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ°éĿ¢
    -0.30
    >{$
    -0.28
    å½±åĥı
    -0.28
    ocy
    -0.26
    奥æŀĹ
    -0.26
     Clips
    -0.24
     topology
    -0.24
     Commit
    -0.24
    æģ¤
    -0.24
    ám
    -0.23
    POSITIVE LOGITS
     ÑĩиÑģле
    0.26
    fin
    0.26
    zej
    0.25
    caf
    0.25
     Sawyer
    0.24
    adle
    0.24
    dT
    0.24
    lett
    0.24
    âĭĦ
    0.23
     financial
    0.23
    Activations Density 9.180%

    No Known Activations

    This feature has no known activations.