© 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. 86837
    Prev
    Next
    INDEX
    Explanations

    about

    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
    Instructions
    -0.26
    ettel
    -0.25
    åĵ¨
    -0.25
    راÙģ
    -0.25
     Goth
    -0.24
    NB
    -0.24
    Extras
    -0.24
    æļĤæŶ
    -0.24
     ÑĥÑģÑĤанов
    -0.23
     rá
    -0.23
    POSITIVE LOGITS
    [table
    0.28
    %C
    0.27
    \Persistence
    0.26
    å¿łå®ŀ
    0.26
    ~~~~~~~~
    0.26
    ewise
    0.25
    ä¼Łå¤§çļĦ
    0.24
     <%
    0.23
    awah
    0.23
    idable
    0.23
    Activations Density 0.021%

    No Known Activations