© 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. 19-TRANSCODER-HP
    7. 9470
    Prev
    Next
    INDEX
    Explanations

    programming and software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Van
    -0.26
     newIndex
    -0.26
    Roy
    -0.25
    itative
    -0.25
    axy
    -0.25
    ufig
    -0.25
     stemming
    -0.25
    stein
    -0.25
    viron
    -0.24
     Hoch
    -0.24
    POSITIVE LOGITS
    éī´
    0.29
    LObject
    0.27
    èĨ³
    0.26
    ä¹Łä¸įä¾ĭå¤ĸ
    0.26
    马æĭī
    0.26
    â¾Ķ
    0.25
    æķĻèĤ²åŁ¹è®Ń
    0.24
     disturb
    0.24
     contender
    0.23
     Projectile
    0.23
    Activations Density 0.089%

    No Known Activations