© 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. 41669
    Prev
    Next
    INDEX
    Explanations

    tests, studies

    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
    unist
    -0.25
     fadeIn
    -0.24
    Solo
    -0.24
    graf
    -0.24
     RoutedEventArgs
    -0.24
     fucking
    -0.24
    å¼Ħ
    -0.24
    å¼Ħå¾Ĺ
    -0.24
    corn
    -0.24
    htdocs
    -0.24
    POSITIVE LOGITS
    ampa
    0.31
    omba
    0.31
    -shell
    0.27
    Tesla
    0.26
    ev
    0.26
    nı
    0.25
    lsa
    0.25
    æľ¬æĬ¥è®¯
    0.25
    ental
    0.25
    Accessible
    0.25
    Activations Density 3.478%

    No Known Activations