© 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. 39738
    Prev
    Next
    INDEX
    Explanations

    x

    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
    æł¹æľ¬å°±ä¸į
    -0.25
    affen
    -0.25
    PR
    -0.25
    æĴĴ
    -0.24
    Perfect
    -0.24
    ât
    -0.24
    ghan
    -0.24
    æĮĩçļĦæĺ¯
    -0.24
    Sign
    -0.23
    ä½łä»¥ä¸º
    -0.23
    POSITIVE LOGITS
     guard
    0.30
    stor
    0.28
     guards
    0.26
     Booth
    0.26
    abyte
    0.25
    หมà¸Ķ
    0.25
    antro
    0.25
    ently
    0.25
     horsepower
    0.24
    èĩªèIJ¥
    0.24
    Activations Density 0.324%

    No Known Activations