© 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. 18927
    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
     appearance
    -0.29
     appearing
    -0.26
    æ¡´
    -0.25
     rede
    -0.24
     forwards
    -0.23
    ificant
    -0.23
     inward
    -0.23
     registr
    -0.23
     upwards
    -0.23
    ged
    -0.23
    POSITIVE LOGITS
    å¾ģ
    0.30
     poster
    0.29
    poster
    0.27
     Poster
    0.25
    å¾ģéĽĨ
    0.25
    éģ£
    0.24
    èµ°
    0.24
     TokenType
    0.24
     Tickets
    0.24
     беÑģплаÑĤно
    0.24
    Activations Density 12.681%

    No Known Activations

    This feature has no known activations.