© 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. 129327
    Prev
    Next
    INDEX
    Explanations

    to

    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
    LOS
    -0.27
    codes
    -0.26
    iness
    -0.26
    urb
    -0.24
    uku
    -0.24
    INAL
    -0.24
    _REFERENCE
    -0.24
    å°±åĥı
    -0.24
     dni
    -0.24
    ç²½åŃIJ
    -0.23
    POSITIVE LOGITS
     avail
    0.28
    è°ģçŁ¥éģĵ
    0.28
    icz
    0.28
    Txt
    0.27
    ripe
    0.25
     gesture
    0.25
    antal
    0.25
    oce
    0.25
    æĪIJçĨŁçļĦ
    0.24
    arih
    0.24
    Activations Density 15.354%

    No Known Activations