© 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. 29372
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    bek
    -0.28
    /rem
    -0.27
    çŁ³å¤´
    -0.26
     prospects
    -0.25
    igan
    -0.24
     bott
    -0.24
     remain
    -0.24
    ãĤ·ãĥ³
    -0.24
    icle
    -0.24
    æľĿ
    -0.24
    POSITIVE LOGITS
    uxtap
    0.31
     Servlet
    0.27
    edriver
    0.26
    æĹıèĩªæ²»åİ¿
    0.26
    æݧèĤ¡
    0.26
     sponsored
    0.26
     kms
    0.24
    &W
    0.24
     Mounted
    0.24
    çĭĪ
    0.24
    Activations Density 2.610%

    No Known Activations