© 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. 9031
    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
    alom
    -0.31
    åħļçļĦé¢Ĩ导
    -0.29
    heimer
    -0.28
    ä¸Ŀä¸Ŀ
    -0.28
    éĢļ
    -0.27
    ÑĥÑĩа
    -0.26
    åĭ¤
    -0.26
    oop
    -0.26
     ASF
    -0.26
    æĥħ
    -0.25
    POSITIVE LOGITS
    é¹Ĥ
    0.29
    åºĹéĩĮ
    0.28
     BELOW
    0.28
    Tester
    0.27
     Lowest
    0.26
    pez
    0.25
    ä¸ĭéĿ¢å°±
    0.25
    åŃIJéĩĮ
    0.25
     Strike
    0.24
     tester
    0.24
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.