© 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. 19-TRANSCODER-HP
    7. 9344
    Prev
    Next
    INDEX
    Explanations

    Contrastive conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _principal
    -0.27
     hạ
    -0.26
    gan
    -0.25
     innovate
    -0.25
     innovation
    -0.25
     coup
    -0.25
     moc
    -0.25
    iamond
    -0.24
     Asked
    -0.24
     dance
    -0.24
    POSITIVE LOGITS
    phis
    0.31
    ampp
    0.30
    aldo
    0.27
    æĪªæŃ¢
    0.27
    omet
    0.26
    ä¼ĬåĪ©
    0.26
    afc
    0.26
    ocomplete
    0.26
    å¸ĮæľĽ
    0.26
    ä¸į幸
    0.25
    Activations Density 0.034%

    No Known Activations