© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7055
    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
    æ±Ĥ
    -0.29
    ellig
    -0.26
    棱
    -0.26
     reinforcement
    -0.25
    bis
    -0.25
    éĩįè§Ĩ
    -0.25
     dạ
    -0.25
    éĶIJ
    -0.25
    微信åħ¬ä¼Ĺ
    -0.25
    ç¦Ģ
    -0.24
    POSITIVE LOGITS
     cast
    0.26
     aside
    0.25
    pmat
    0.25
    .defer
    0.25
    lift
    0.24
    éĻIJé¢Ŀ
    0.24
    avra
    0.24
    )did
    0.24
    ;base
    0.24
    çĭ¸
    0.24
    Activations Density 0.087%

    No Known Activations

    This feature has no known activations.