© 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. 64438
    Prev
    Next
    INDEX
    Explanations

    Words that can begin sentences

    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
    è§Ħç¨ĭ
    -0.27
     cris
    -0.27
    å®ŀåľ¨æĺ¯
    -0.25
    å®ŀåľ¨æĺ¯å¤ª
    -0.25
    å½ĵçĦ¶æĺ¯
    -0.24
    bearing
    -0.24
     surely
    -0.24
    thinkable
    -0.24
     THANK
    -0.24
    æĺ¾çĦ¶æĺ¯
    -0.24
    POSITIVE LOGITS
    udad
    0.26
    EOS
    0.25
    |)↵
    0.25
    ç¿ł
    0.25
     ters
    0.25
    iliki
    0.24
     Klo
    0.24
    isser
    0.24
    .Requires
    0.24
    andi
    0.23
    Activations Density 24.375%

    No Known Activations