© 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. 19250
    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
    lew
    -0.28
    说æ³ķ
    -0.27
    arie
    -0.26
    è¿ĺæľīä»Ģä¹Ī
    -0.25
     McCorm
    -0.25
     multiline
    -0.25
    ,tmp
    -0.24
    è¿ĻæĿ¡
    -0.24
    dcc
    -0.24
    /LICENSE
    -0.24
    POSITIVE LOGITS
    åħ¶æ¬¡
    0.26
     loaf
    0.26
    asking
    0.26
     baÅŁÄ±na
    0.26
    èĢ³
    0.26
    åĢĴ
    0.25
    PROTO
    0.24
    ous
    0.24
    _prim
    0.23
    许
    0.23
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.