© 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. 23-TRANSCODER-HP
    7. 23435
    Prev
    Next
    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éģı
    -0.32
    è´
    -0.30
    urent
    -0.26
    å¥¥åľ°
    -0.26
    æĹıèĩªæ²»åİ¿
    -0.26
    åµİ
    -0.24
    æµģåĩº
    -0.24
    æĭĽèģĺä¿¡æģ¯
    -0.24
    è¶Ĭ
    -0.24
     sprung
    -0.24
    POSITIVE LOGITS
     nearly
    0.34
     approximately
    0.31
    ials
    0.29
    约
    0.28
     millions
    0.28
     billion
    0.27
    bff
    0.27
     reasonable
    0.26
     consistently
    0.26
    大约
    0.26
    Activations Density 0.005%

    No Known Activations