© 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. 109195
    Prev
    Next
    INDEX
    Explanations

    code and miscellaneous 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
    Not in Any Lists

    No Comments

    Negative Logits
    NotFoundError
    -0.27
    蹶
    -0.27
     nø
    -0.26
    å¢Ł
    -0.25
    æĬĺ
    -0.25
    ĻĤ
    -0.25
    å·¡åĽŀ
    -0.24
    едеÑĢ
    -0.23
     conferences
    -0.23
    侧
    -0.23
    POSITIVE LOGITS
     homework
    0.52
    ä½ľä¸ļ
    0.44
    åľ¨å®¶
    0.42
    Hom
    0.39
     Homework
    0.38
    hom
    0.37
     HOME
    0.35
    _hom
    0.35
     HW
    0.34
    家çĶ¨
    0.33
    Activations Density 0.908%

    No Known Activations