© 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. 32-TRANSCODER-HP
    7. 43446
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -0.48
     There
    -0.46
    There
    -0.43
     theres
    -0.42
    there
    -0.42
    å°±æľī
    -0.41
    ä¹Łæľī
    -0.38
    æĽ´æľī
    -0.37
    ther
    -0.36
    æľīä¸Ģ
    -0.36
    POSITIVE LOGITS
    Are
    0.38
     Are
    0.36
    åĿĩ
    0.33
    éĥ½æĺ¯
    0.31
    éĥ½åı¯ä»¥
    0.30
    åĿĩåı¯
    0.29
    _are
    0.28
    asel
    0.28
    åĿĩ为
    0.27
    éĥ½è¢«
    0.27
    Activations Density 0.007%

    No Known Activations