© 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. 9-TRANSCODER-HP
    7. 30328
    Prev
    Next
    INDEX
    Explanations

    technical/scientific concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ../../../
    -0.28
     Annex
    -0.27
     UNITY
    -0.27
    ä¸įæĥľ
    -0.26
    .layer
    -0.25
    ico
    -0.24
     Howard
    -0.24
    upo
    -0.24
    akit
    -0.24
     tongue
    -0.23
    POSITIVE LOGITS
    orc
    0.28
    æ·¦
    0.26
    combe
    0.26
    æŀķ头
    0.25
    typeorm
    0.25
     fiber
    0.24
    ç²¾åįİ
    0.24
    Ùħد
    0.24
     Interr
    0.24
     three
    0.23
    Activations Density 0.684%

    No Known Activations