© 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. 18-TRANSCODER-HP
    7. 88885
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anela
    -0.31
     ser
    -0.29
    adf
    -0.28
    ç»Ī
    -0.28
    ego
    -0.27
    ä¸ĸ代
    -0.27
     sk
    -0.27
    rol
    -0.27
    串
    -0.26
    ks
    -0.25
    POSITIVE LOGITS
    åħ³äºİæĪij们
    0.30
    erge
    0.28
    Reverse
    0.27
    æł¹æį®èĩªå·±
    0.26
    arth
    0.26
    ustum
    0.25
    就已ç»ı
    0.25
    -gap
    0.25
    å¼Ģè¾Ł
    0.25
    ighth
    0.25
    Activations Density 12.679%

    No Known Activations

    This feature has no known activations.