© 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. 18822
    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
    erm
    -0.31
    иÑĢÑĥем
    -0.26
     terms
    -0.25
    imations
    -0.25
     coloc
    -0.24
    -eff
    -0.24
    enger
    -0.24
    cej
    -0.23
    adata
    -0.23
     more
    -0.23
    POSITIVE LOGITS
    ToDevice
    0.28
    çīĮåŃIJ
    0.27
    æĹıèĩªæ²»åİ¿
    0.27
    _bases
    0.27
    太é«ĺ
    0.26
    ä¸Ģèĩ´
    0.26
     roar
    0.26
    ;base
    0.26
     Phrase
    0.26
     "&#
    0.25
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.