© 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. 95077
    Prev
    Next
    INDEX
    Explanations

    is or are

    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
     subject
    -0.33
     Doc
    -0.32
    _attached
    -0.31
    æĸĩæ¡£
    -0.30
     document
    -0.30
     doc
    -0.29
    Docs
    -0.29
    /doc
    -0.29
    Doc
    -0.28
     docs
    -0.28
    POSITIVE LOGITS
    odo
    0.32
    -now
    0.28
     Now
    0.27
    ForObject
    0.26
    .now
    0.25
     Grat
    0.25
    åĽ½å®¶
    0.25
    èĩª
    0.25
    <tag
    0.25
    èĮ§
    0.24
    Activations Density 0.107%

    No Known Activations