© 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. 109443
    Prev
    Next
    INDEX
    Explanations

    Scientific publications

    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
    çľĭä»ĸ
    -0.31
    Sibling
    -0.27
    rollback
    -0.25
    毡
    -0.25
    èµ·äºĨ
    -0.24
    alar
    -0.24
    optional
    -0.24
     kaz
    -0.24
    ulet
    -0.24
    dal
    -0.24
    POSITIVE LOGITS
     Drain
    0.27
    aternity
    0.24
    olen
    0.24
     av
    0.24
    avin
    0.24
     Whole
    0.24
     Pruitt
    0.23
    >Please
    0.23
    uttle
    0.23
    ä¸įè´Ł
    0.23
    Activations Density 0.171%

    No Known Activations