© 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. 109505
    Prev
    Next
    INDEX
    Explanations

    law

    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
    HU
    -0.30
    hu
    -0.27
    cot
    -0.26
    _bn
    -0.26
    è·ĥ
    -0.25
     rented
    -0.25
    aber
    -0.25
    ppers
    -0.24
     ni
    -0.24
    秣èµģ
    -0.24
    POSITIVE LOGITS
     system
    0.31
    (system
    0.31
    èħ±
    0.30
    \system
    0.29
    system
    0.29
     há»ĩ
    0.28
     tá»ĩ
    0.27
    çĸ²
    0.27
    ç³»ç»Ł
    0.26
     sistema
    0.26
    Activations Density 0.185%

    No Known Activations