© 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. 31-TRANSCODER-HP
    7. 19810
    Prev
    Next
    INDEX
    Explanations

    review

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĢĨè¡Į
    -0.30
    丼
    -0.28
    渥
    -0.27
    æ³³
    -0.26
    Videos
    -0.25
    spread
    -0.25
    ç»į
    -0.25
    emade
    -0.24
    å¼ĵ
    -0.24
    éĶĭ
    -0.24
    POSITIVE LOGITS
     SYN
    0.32
     paper
    0.32
     publish
    0.31
    publish
    0.31
     synthesis
    0.31
    ABS
    0.31
    论æĸĩ
    0.30
     publication
    0.30
     absorption
    0.29
     published
    0.29
    Activations Density 1.769%

    No Known Activations