© 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. 9-TRANSCODER-HP
    7. 29475
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ald
    -0.33
    lopen
    -0.29
    émon
    -0.28
    izio
    -0.28
    DataAdapter
    -0.25
    _UUID
    -0.24
    าย
    -0.24
    ?>↵
    -0.24
     Biological
    -0.24
    semblies
    -0.24
    POSITIVE LOGITS
     poil
    0.27
    æĿ¾å¼Ľ
    0.26
    lations
    0.26
     sizing
    0.25
    å®
    0.24
    åIJ¬åĪ°
    0.24
    躺
    0.24
     wiÄĻ
    0.24
     relaxation
    0.23
    CES
    0.23
    Activations Density 0.551%

    No Known Activations