© 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. 20-TRANSCODER-HP
    7. 129524
    Prev
    Next
    INDEX
    Explanations

    code, data, math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨ä»ĸ
    -0.28
    åijĬè¯īä»ĸ
    -0.26
    éĵ¶è¡Įä¸ļ
    -0.25
    åĽĽä¸ªæĸ¹éĿ¢
    -0.24
    Anyway
    -0.24
    å°ıäºĭ
    -0.24
    loid
    -0.24
     Ped
    -0.24
     Anyway
    -0.23
    éŨè¯Ĭ
    -0.23
    POSITIVE LOGITS
    åĽ¾ä¸º
    0.27
    æŁ´
    0.27
     advocated
    0.26
    IJèĹı
    0.26
     similarly
    0.26
    éħįæľī
    0.25
     Laurel
    0.25
    rade
    0.24
     *)&
    0.24
    itary
    0.24
    Activations Density 33.300%

    No Known Activations