© 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. 20-TRANSCODER-HP
    7. 64712
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    以èī²
    -0.28
    ÑİÑĢ
    -0.27
    iors
    -0.25
    icine
    -0.24
    éĿ¢ä¸´
    -0.24
    bac
    -0.24
    overs
    -0.24
    .reject
    -0.24
    npos
    -0.24
    lesia
    -0.23
    POSITIVE LOGITS
    athi
    0.28
    ’)
    0.28
    &,
    0.27
    éĹ²ç½®
    0.25
    &amp
    0.25
    (mut
    0.24
     silence
    0.24
    )&
    0.23
    ’,
    0.23
    >,</
    0.23
    Activations Density 12.207%

    No Known Activations