© 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. 27-TRANSCODER-HP
    7. 7673
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç³Ĭæ¶Ĥ
    -0.27
    ê°IJ
    -0.27
     excavation
    -0.26
    estone
    -0.26
     digging
    -0.26
    arium
    -0.26
    åĸģ
    -0.26
     ç±
    -0.25
    æij¸
    -0.25
    æĮĸæİĺ
    -0.25
    POSITIVE LOGITS
    \Migration
    0.30
     addCriterion
    0.29
    ä¸ĩåħĥ以ä¸Ĭ
    0.29
    vol
    0.28
    .setPrototypeOf
    0.27
    airo
    0.26
    @student
    0.25
    æľįåĬ¡ä¸Ńå¿ĥ
    0.25
    éĻĮçĶŁäºº
    0.25
     occupations
    0.25
    Activations Density 0.000%

    No Known Activations