© 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. 18527
    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
    arkan
    -0.31
    .$.
    -0.28
    马åħĭ
    -0.26
     african
    -0.25
    åį±
    -0.25
    enger
    -0.24
    è´¨
    -0.24
    ASY
    -0.24
    $",
    -0.24
    `).
    -0.23
    POSITIVE LOGITS
     misc
    0.32
    åŁºæķ°
    0.31
    å½ķçĶ¨
    0.27
    Launching
    0.26
    isée
    0.25
    æĸ°åĨľæĿij
    0.24
     offset
    0.24
     dock
    0.24
    canf
    0.24
     bra
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.