© 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. 8629
    Prev
    Next
    INDEX
    Explanations

    varied text sources

    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
    åı¸
    -0.33
    éĢĨ
    -0.25
    isel
    -0.24
    loy
    -0.24
    ASSERT
    -0.24
    isclosed
    -0.23
    Ñģим
    -0.23
    ashing
    -0.23
     Roz
    -0.23
    collapse
    -0.23
    POSITIVE LOGITS
     caus
    0.29
    å¢ŀ
    0.27
    urnal
    0.24
    ä½łä¼ļ
    0.24
    è¾ĺ
    0.24
    ë§Ŀ
    0.23
    çļĦæĸ¹å¼ıæĿ¥
    0.23
    CW
    0.23
    çļĦè¯Ŀ
    0.23
     curt
    0.23
    Activations Density 0.012%

    No Known Activations