© 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. 18-TRANSCODER-HP
    7. 90098
    Prev
    Next
    INDEX
    Explanations

    humans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĩ³æѤ
    -0.30
    ä¿ĿçķĻ
    -0.29
    èĨı
    -0.29
    ä»İä¸ļ
    -0.27
    quisite
    -0.25
    efs
    -0.25
    sumer
    -0.25
    ä¸ĢåįĬ
    -0.25
     ADV
    -0.24
    ipping
    -0.24
    POSITIVE LOGITS
    ait
    0.27
    whereIn
    0.26
     Bates
    0.25
    Ľå»º
    0.25
    -machine
    0.24
    ç»Ļå®Ŀå®Ŀ
    0.24
    iez
    0.24
    -Al
    0.23
     sarc
    0.23
    ег
    0.23
    Activations Density 14.324%

    No Known Activations