© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141673
    Prev
    Next
    INDEX
    Explanations

    Software development

    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
    æĸ°å½¢åĬ¿
    -0.29
    ç»ĻåŃ©åŃIJ
    -0.24
    peri
    -0.24
    -hole
    -0.24
    gor
    -0.24
    vang
    -0.24
    享åıĹåĪ°
    -0.24
     ÑĤакое
    -0.23
    cess
    -0.23
    IMS
    -0.23
    POSITIVE LOGITS
    并å°Ĩ
    0.29
     ob
    0.28
     shorts
    0.27
    etsy
    0.27
     bÃło
    0.25
    ÑĥменÑĤ
    0.24
    并ä¸İ
    0.24
    navigate
    0.24
    MENU
    0.24
    å¹³åĿĩæ°´å¹³
    0.24
    Activations Density 17.918%

    No Known Activations