© 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. 63904
    Prev
    Next
    INDEX
    Explanations

    code, configuration, technical information

    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
    ué
    -0.28
    èĨ³
    -0.28
    aly
    -0.27
    ÙĬرة
    -0.26
    omy
    -0.26
    ä¸Ĭçľĭ
    -0.25
    /&
    -0.25
     Undert
    -0.25
    oload
    -0.25
    èIJ½
    -0.25
    POSITIVE LOGITS
     dar
    0.26
    èİĺ
    0.26
     aras
    0.25
    ä¸įç»ıæĦı
    0.25
    积水
    0.24
    çĮ¬
    0.24
    å°Ĩè¿ij
    0.24
    æĬ¥è®°èĢħ
    0.24
    æĿĥéĻIJ
    0.24
     kolej
    0.24
    Activations Density 1.237%

    No Known Activations