© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7617
    Prev
    Next
    INDEX
    Explanations

    Biographies

    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
    iat
    -0.30
     interest
    -0.25
    æ·ĩ
    -0.24
    ÙĬÙģ
    -0.24
    ä»ĸåľ¨
    -0.24
    quals
    -0.24
    åŀĥåľ¾æ¡¶
    -0.24
     vanilla
    -0.23
     bằng
    -0.23
     =================================================================================
    -0.23
    POSITIVE LOGITS
    weis
    0.28
    æ¯ķç«Ł
    0.28
     thankfully
    0.28
    ÑĢей
    0.28
    ений
    0.26
    abouts
    0.25
    lest
    0.25
    alloc
    0.24
    éĹ³
    0.24
    人人éĥ½
    0.24
    Activations Density 0.094%

    No Known Activations