© 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. 57865
    Prev
    Next
    INDEX
    Explanations

    changes in

    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
    INGS
    -0.09
    åĴĮæľįåĬ¡
    -0.09
    omics
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    客æĪ·æıIJä¾Ľ
    -0.08
    ingroup
    -0.08
    CharArray
    -0.08
    estre
    -0.08
    gings
    -0.08
    otime
    -0.08
    POSITIVE LOGITS
     how
    0.10
    .prof
    0.10
    /off
    0.10
    Äł
    0.10
    /im
    0.09
    ç´§å¼ł
    0.09
    å·¥ä½ľä½ľé£İ
    0.09
    俾
    0.09
     ÐŁÐ¾Ñĩ
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    Activations Density 0.104%

    No Known Activations