© 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. 130806
    Prev
    Next
    INDEX
    Explanations

    Science, technology, administration

    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
    å®ŀä½ĵ
    -0.27
     entityId
    -0.26
    	Entity
    -0.26
     Annex
    -0.26
     entity
    -0.26
     Ded
    -0.26
    plib
    -0.25
    SYM
    -0.25
     privat
    -0.25
    arendra
    -0.24
    POSITIVE LOGITS
    ÅĻ
    0.24
    /cs
    0.24
    顾
    0.24
    硬
    0.24
    rez
    0.23
    æī¿æĭħ责任
    0.23
    _abs
    0.23
    gue
    0.23
    urr
    0.23
     xuất
    0.23
    Activations Density 18.858%

    No Known Activations