© 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. 129375
    Prev
    Next
    INDEX
    Explanations

    Code and programming language

    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
     compos
    -0.31
    .setGeometry
    -0.30
    缴æİ¥
    -0.29
    éĹ´æİ¥
    -0.29
     indirect
    -0.28
     concurrent
    -0.27
     direct
    -0.27
     included
    -0.27
     directly
    -0.26
    unya
    -0.26
    POSITIVE LOGITS
    èĥ½è¾¾åĪ°
    0.32
    满æĦıçļĦ
    0.31
     satisfactory
    0.29
    èĥ½æ»¡è¶³
    0.28
    likely
    0.27
    çļĦåĽŀçŃĶ
    0.27
     comfortably
    0.26
    满æĦı
    0.26
    çļĦæĢģ度
    0.25
     readiness
    0.25
    Activations Density 54.490%

    No Known Activations