© 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. 19357
    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
     Back
    -0.26
     JO
    -0.26
    éĿ©
    -0.26
    -short
    -0.26
     Material
    -0.26
    æľŁ
    -0.25
     material
    -0.25
    _scheme
    -0.25
    -db
    -0.25
    WithType
    -0.25
    POSITIVE LOGITS
    é¤į
    0.28
    stitial
    0.24
    ç£IJ
    0.24
    faction
    0.24
     brakes
    0.24
     blurred
    0.23
    etime
    0.23
     [[]
    0.23
    (exports
    0.23
     Ferdinand
    0.23
    Activations Density 4.134%

    No Known Activations

    This feature has no known activations.