© 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. 108430
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     purs
    -0.29
    HING
    -0.27
    çªĺ
    -0.27
    stin
    -0.27
    ç¾¹
    -0.25
    Wo
    -0.25
    æĤ¨å¥½
    -0.25
    pst
    -0.24
     sunglasses
    -0.24
     fats
    -0.24
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.33
    ä¸ĢèĪ¬çļĦ
    0.31
    ä¼łç»Ł
    0.31
    ordinary
    0.29
    æĻ®éĢļçļĦ
    0.28
     IMessage
    0.27
     slides
    0.27
    æµĩ
    0.25
    trag
    0.25
    Traditional
    0.25
    Activations Density 56.880%

    No Known Activations