© 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. 8596
    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
     haze
    -0.26
    æīĢæıIJä¾Ľ
    -0.24
     Province
    -0.24
    _MACHINE
    -0.24
    lian
    -0.24
    iov
    -0.24
    ISK
    -0.23
    ä¹°åįķ
    -0.23
    sume
    -0.23
    tog
    -0.23
    POSITIVE LOGITS
    ä½ľä¸º
    0.25
    ç¿»
    0.25
    å¼Ģ
    0.25
    peater
    0.24
     as
    0.24
    ä¸Ģ声
    0.23
    İ·
    0.23
    ocom
    0.23
     wrench
    0.23
    'in
    0.23
    Activations Density 0.068%

    No Known Activations

    This feature has no known activations.