© 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. 129266
    Prev
    Next
    INDEX
    Explanations

    (

    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
    å®Įæķ´çļĦ
    -0.27
     LET
    -0.27
    Let
    -0.27
    å®Įæķ´
    -0.26
     æĪĸ
    -0.26
    æĶ¶
    -0.26
    LET
    -0.26
     Let
    -0.26
    让æĤ¨
    -0.25
     let
    -0.25
    POSITIVE LOGITS
    oose
    0.31
    ä½Ĩ对äºİ
    0.26
    主ä½ĵ
    0.26
    ãģªãģĮãĤī
    0.25
    æĮĩçĿĢ
    0.25
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    —but
    0.24
    äºİ
    0.24
    OLD
    0.23
     gro
    0.23
    Activations Density 0.003%

    No Known Activations