© 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. 22-TRANSCODER-HP
    7. 129247
    Prev
    Next
    INDEX
    Explanations

    returning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩįæĸ°
    -0.76
    åĨį次
    -0.71
     renewed
    -0.69
    åĨį度
    -0.69
     again
    -0.68
    éĩįè¿Ķ
    -0.67
    æģ¢å¤į
    -0.67
     reinst
    -0.66
     resurgence
    -0.64
     restored
    -0.63
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.31
    æĪIJéķ¿ä¸º
    0.26
    æıŃ
    0.25
     æı
    0.24
    æĹ¥æŃ£å¼ı
    0.24
    infer
    0.24
    æŃ£å¼ı
    0.24
     prelim
    0.24
     preliminary
    0.23
    åĩij
    0.23
    Activations Density 0.014%

    No Known Activations