© 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. 108247
    Prev
    Next
    INDEX
    Explanations

    conversational text

    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
    æĤ«
    -0.27
    åħ·
    -0.27
    entlich
    -0.25
    legt
    -0.25
    ç§ĺ书éķ¿
    -0.25
     Cycling
    -0.24
    tributes
    -0.24
    òn
    -0.23
    brook
    -0.23
    æ³Ħ
    -0.23
    POSITIVE LOGITS
    hoff
    0.28
    atori
    0.26
    äºĮ代
    0.25
    åŁİ乡å±ħæ°ij
    0.24
    it
    0.24
    Jane
    0.24
    ç¥ŀå·ŀ
    0.24
    æ¸ļ
    0.23
    :description
    0.23
     damp
    0.23
    Activations Density 44.110%

    No Known Activations