© 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. 56323
    Prev
    Next
    INDEX
    Explanations

    1

    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
    表éĿ¢
    -0.27
    è¿ĿèĥĮ
    -0.26
    infeld
    -0.26
    ulk
    -0.25
     Iter
    -0.24
    Clock
    -0.24
    æĹģ
    -0.24
     basis
    -0.24
    左侧
    -0.24
    serter
    -0.24
    POSITIVE LOGITS
     ÑģÑĦ
    0.27
     affected
    0.27
    æ³½
    0.26
    endon
    0.26
     temporary
    0.25
    çĸ«æĥħæľŁéĹ´
    0.25
    éľĩèį¡
    0.25
    æĮģãģ¡
    0.25
    ç¼ĵ
    0.25
    lus
    0.25
    Activations Density 0.006%

    No Known Activations