© 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. 27-TRANSCODER-HP
    7. 56481
    Prev
    Next
    INDEX
    Explanations

    math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¯Ķä¾ĭ
    -0.31
    åįıä¼ļä¼ļåijĺ
    -0.28
    çļĦæ¯Ķä¾ĭ
    -0.26
    ogene
    -0.26
    ESH
    -0.25
     liners
    -0.25
    æľŁéĻIJ
    -0.24
     meas
    -0.24
    示èĮĥåŁºåľ°
    -0.24
    )|(
    -0.24
    POSITIVE LOGITS
     largest
    0.32
    å¼¹
    0.29
    is
    0.28
     workload
    0.28
    è´¢
    0.27
    (console
    0.26
    ia
    0.26
    eval
    0.25
    äºij
    0.25
     highest
    0.25
    Activations Density 0.003%

    No Known Activations