© 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. 107039
    Prev
    Next
    INDEX
    Explanations

    interrupted text

    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
    Negative Logits
    ç³Ł
    -0.29
     privat
    -0.29
    æİĮæݧ
    -0.27
    /lic
    -0.26
    è´¯
    -0.26
     Osw
    -0.25
    ä»ĩ
    -0.25
    ifold
    -0.24
    çĿ£
    -0.24
    mailto
    -0.24
    POSITIVE LOGITS
    åģľ
    0.63
     pause
    0.58
     pauses
    0.54
    åģľä¸ĭæĿ¥
    0.54
    åģľçķĻ
    0.53
     paused
    0.52
    çĬ¹è±«
    0.50
    åģľä¸ĭ
    0.49
     Pause
    0.48
    pause
    0.48
    Activations Density 0.974%

    No Known Activations