© 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. 9161
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash
    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
     AW
    -0.31
     SCT
    -0.28
    ROC
    -0.27
     {_
    -0.27
    ç²Ł
    -0.26
    aec
    -0.25
     PSU
    -0.25
     EX
    -0.24
    SenderId
    -0.24
    .tt
    -0.24
    POSITIVE LOGITS
    cade
    0.29
    .deb
    0.27
    éĩį
    0.26
    ä½ĵåĪ¶
    0.24
    å¼ĢèĬ±
    0.24
    alité
    0.24
    è¡Įæĥħ
    0.23
     uyar
    0.23
    æł¼
    0.23
     Downing
    0.23
    Activations Density 0.076%

    No Known Activations