© 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. 30-TRANSCODER-HP
    7. 94935
    Prev
    Next
    INDEX
    Explanations

    author and authors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    och
    -0.27
    侪
    -0.27
    ille
    -0.25
    ILLE
    -0.25
    onen
    -0.25
    æݧèĤ¡
    -0.25
    iddled
    -0.25
    endi
    -0.24
    _pb
    -0.24
     pleas
    -0.23
    POSITIVE LOGITS
    ä½ľèĢħ
    1.66
     author
    1.65
     Author
    1.45
     authors
    1.39
    author
    1.38
    Author
    1.34
    -author
    1.21
     Authors
    1.19
    .author
    1.16
     autor
    1.16
    Activations Density 0.891%

    No Known Activations