© 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. 62936
    Prev
    Next
    INDEX
    Explanations

    -

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .’
    -0.27
     spell
    -0.25
    .'
    -0.25
    ás
    -0.25
    utos
    -0.24
    大å°ı
    -0.24
     other
    -0.24
    æµİ
    -0.24
    --
    -0.24
     minority
    -0.24
    POSITIVE LOGITS
     Ranked
    0.27
     Tune
    0.27
     Balt
    0.27
    =count
    0.27
    elled
    0.26
    kest
    0.26
    icans
    0.25
    otify
    0.25
    abis
    0.25
    fault
    0.24
    Activations Density 1.664%

    No Known Activations