© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107257
    Prev
    Next
    INDEX
    Explanations

    political/historical comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tits
    -0.26
    nox
    -0.26
    å¤ļå±Ĥ次
    -0.26
    .IGNORE
    -0.26
     pii
    -0.26
    æĹłè§Ĩ
    -0.25
    ä¸īæĸ¹
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    izen
    -0.24
    妨
    -0.24
    POSITIVE LOGITS
    ä¹ĭåŁİ
    0.27
    æĮ
    0.26
    fore
    0.25
    ÎĨ
    0.25
    QueryString
    0.24
    compiler
    0.24
    é£İåħī
    0.24
    åºĶæĢ¥é¢Ħæ¡Ī
    0.24
    _business
    0.24
    ará
    0.24
    Activations Density 0.931%

    No Known Activations