© 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. 8289
    Prev
    Next
    INDEX
    Explanations

    old

    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
    {return
    -0.26
    .await
    -0.26
    (return
    -0.26
    å¼Ĥ
    -0.25
    IRECT
    -0.25
    TAIL
    -0.25
    æļĩ
    -0.25
     wczeÅĽniej
    -0.25
    PHONE
    -0.24
    .return
    -0.24
    POSITIVE LOGITS
     ones
    0.27
    Łèĥ½
    0.26
     squ
    0.26
    碧
    0.26
    izations
    0.25
     level
    0.25
    lor
    0.24
    -level
    0.23
     sust
    0.23
     sustainable
    0.23
    Activations Density 0.014%

    No Known Activations