© 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. 41413
    Prev
    Next
    INDEX
    Explanations

    Ware

    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
    checked
    -0.25
    é¢ł
    -0.25
    orna
    -0.24
    едÑĮ
    -0.24
     reps
    -0.24
    æĪijåĴĮ
    -0.24
    cala
    -0.23
    iom
    -0.23
     ATK
    -0.23
    styled
    -0.23
    POSITIVE LOGITS
    otions
    0.29
    çŀ¬
    0.26
    kir
    0.25
    histor
    0.25
    otional
    0.25
    æİĴè¡Į
    0.24
    åıĶ
    0.24
    符
    0.24
     wag
    0.23
    延伸
    0.23
    Activations Density 0.318%

    No Known Activations