© 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. 14-TRANSCODER-HP
    7. 41431
    Prev
    Next
    INDEX
    Explanations

    computer software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocard
    -0.29
    æĪIJåĬŁçļĦ
    -0.27
    对æīĭ
    -0.26
    ä¸ĩæĪ·
    -0.26
    æķ£
    -0.25
    åĿĩ
    -0.25
    ABS
    -0.25
    outing
    -0.25
     ABS
    -0.25
    åı¤äºº
    -0.25
    POSITIVE LOGITS
     fixed
    0.28
    çłº
    0.26
    rench
    0.26
     finalist
    0.26
    å¸ĮæľĽèĥ½
    0.25
    .instant
    0.25
     hurt
    0.25
    à¹Ģสà¸Ļà¸Ń
    0.25
    ritz
    0.25
    éĻIJæľŁ
    0.25
    Activations Density 0.646%

    No Known Activations