© 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. 113115
    Prev
    Next
    INDEX
    Explanations

    Transitions and additions

    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
    Negative Logits
    èŀ
    -0.26
     оÑģÑĤа
    -0.24
     visibly
    -0.24
    ä½Ĩæĺ¯æĪij
    -0.24
     furthermore
    -0.24
     thereafter
    -0.23
     afterwards
    -0.23
    溯æºIJ
    -0.23
    acula
    -0.23
    uka
    -0.23
    POSITIVE LOGITS
    ä½łåºĶ该
    0.34
     skirt
    0.29
    æĤ¨åı¯ä»¥
    0.28
    prene
    0.27
    çIJĨæĥ³çļĦ
    0.26
    atively
    0.26
    ãģľãģ²
    0.25
    Deprecated
    0.25
    åĢ¼å¾Ĺä¸Ģ
    0.25
    ä¸Ģå®ļè¦ģ
    0.24
    Activations Density 0.003%

    No Known Activations