© 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. 32988
    Prev
    Next
    INDEX
    Explanations

    file extensions like .asm or .org

    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
    çļĦæŃ¥ä¼IJ
    -0.09
    éĥ½æľīèĩªå·±
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.09
    overs
    -0.08
     Gund
    -0.08
    æ·
    -0.08
    rastructure
    -0.08
     overs
    -0.08
    uropean
    -0.08
    errupt
    -0.08
    POSITIVE LOGITS
    èĭį
    0.09
    éĢĢ
    0.09
    èĿĩ
    0.08
    é»Ħéĩij
    0.08
    æĪĴ
    0.08
    coni
    0.08
    ä½ĵçİ°åĩº
    0.08
    è¿ĺæĺ¯ä¼ļ
    0.08
    诰
    0.08
    enza
    0.08
    Activations Density 0.991%

    No Known Activations