© 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. 19-TRANSCODER-HP
    7. 7877
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsch
    -0.31
     sanitation
    -0.28
    è¨Ģ
    -0.28
    ãģ¨ãģ«ãģĭãģı
    -0.27
    ival
    -0.26
     ε
    -0.26
     interpretation
    -0.26
     dem
    -0.26
     ÑĢаз
    -0.25
     dém
    -0.25
    POSITIVE LOGITS
    (coeff
    0.26
    强æľīåĬĽçļĦ
    0.26
    è´Ł
    0.26
    ods
    0.25
    .setTo
    0.25
    æĶ¯éħį
    0.25
    afx
    0.25
    zens
    0.25
    odate
    0.24
     Shops
    0.24
    Activations Density 0.397%

    No Known Activations

    This feature has no known activations.