© 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. 35-TRANSCODER-HP
    7. 40020
    Prev
    Next
    INDEX
    Explanations

    document context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赤
    -0.33
    åĭ¤
    -0.28
    ting
    -0.28
    ooth
    -0.28
    害
    -0.27
    _TA
    -0.26
    循
    -0.25
    家ä½ı
    -0.25
    客
    -0.25
    ap
    -0.25
    POSITIVE LOGITS
    F
    0.27
     toc
    0.26
    ä¹Łä¸įæĥ³
    0.25
     G
    0.24
    åŃĺåľ¨
    0.24
    éĥ½åľ¨
    0.23
    ml
    0.23
    æ¯ı次
    0.23
     Nimbus
    0.23
     attached
    0.22
    Activations Density 59.609%

    No Known Activations