© 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. 41776
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    Negative Logits
    缴æݥ影åĵį
    -0.28
    kir
    -0.28
     пÑĢоÑģÑĤо
    -0.27
    izr
    -0.26
    CRC
    -0.24
    åĬ¨æľº
    -0.24
    åı£æ°´
    -0.24
    actable
    -0.24
    æģIJæĢķ
    -0.23
    mere
    -0.23
    POSITIVE LOGITS
    aget
    0.28
    comed
    0.28
    aeda
    0.28
    ages
    0.27
    ursal
    0.26
    津贴
    0.24
    roll
    0.24
    管çIJĨ人åijĺ
    0.24
    è¯ĹæĦı
    0.24
     vill
    0.23
    Activations Density 1.851%

    No Known Activations