© 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. 58653
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    consin
    -0.28
    пиÑĤ
    -0.28
    arias
    -0.27
    è¿ķ
    -0.25
    æĿ¥è®¿
    -0.25
     cr
    -0.25
    è¯Ħè®®
    -0.25
     welcoming
    -0.24
     pit
    -0.23
    utos
    -0.23
    POSITIVE LOGITS
    æĿ¡
    0.30
    æģ¢å¤įæŃ£å¸¸
    0.28
    æĬ
    0.26
    èł¡
    0.25
    hape
    0.25
    æŁ³
    0.25
    æĬĺ
    0.24
    çĶŁäº§çļĦ
    0.24
    ëĭ´
    0.24
    æ¶Īè´¹èĢħçļĦ
    0.24
    Activations Density 0.070%

    No Known Activations