© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19607
    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
    bourg
    -0.30
    führer
    -0.26
    /channel
    -0.26
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.26
    å¼ĢéĺĶ
    -0.25
    rons
    -0.24
    rale
    -0.24
    èij¡
    -0.24
    körper
    -0.24
    ÑĮÑİ
    -0.24
    POSITIVE LOGITS
    uchi
    0.27
    idas
    0.27
    éĢĤåIJĪèĩªå·±
    0.26
     Cald
    0.25
     refresh
    0.25
    Ajax
    0.25
     sufficiently
    0.25
     piece
    0.25
    _refresh
    0.25
    arcy
    0.25
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.