© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62545
    Prev
    Next
    INDEX
    Explanations

    font and color properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģªãĤĬ
    -0.10
    ButtonModule
    -0.10
    åĴĤ
    -0.10
    åģ¥åº·äº§ä¸ļ
    -0.10
     Headquarters
    -0.09
    庳
    -0.09
    å®ĵ
    -0.09
    èĬĻèĵī
    -0.09
    é£Ĵ
    -0.09
    omal
    -0.09
    POSITIVE LOGITS
    .font
    0.11
    åŃĹä½ĵ
    0.10
     font
    0.09
    çļĦæĸĩåŃĹ
    0.09
    /font
    0.09
    icken
    0.09
     serif
    0.09
     text
    0.09
     fonts
    0.09
    Fonts
    0.09
    Activations Density 0.425%

    No Known Activations