© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    shapes and positions

    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
    atoria
    -0.29
    евиÑĩ
    -0.28
    -comment
    -0.28
    æĮŁ
    -0.28
    ä¸Ģæĸ¹éĿ¢
    -0.27
    excel
    -0.27
     Outreach
    -0.25
     newObj
    -0.24
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.24
    缺åı£
    -0.24
    POSITIVE LOGITS
    度
    0.31
    度è¿ĩ
    0.27
    (pass
    0.26
    oley
    0.26
     ({
    0.25
     lt
    0.25
    inqu
    0.25
    æĥ³è¿ĩ
    0.24
     chance
    0.24
     __
    0.24
    Activations Density 0.007%

    No Known Activations