© 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. 57930
    Prev
    Next
    INDEX
    Explanations

    specifically

    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
    æĭħ
    -0.10
     lẽ
    -0.09
    èĩ³æѤ
    -0.09
    беж
    -0.08
    轶
    -0.08
    æ³ķå®ļ代表
    -0.08
    gba
    -0.08
    è·Ľ
    -0.08
    ä»»ä½ķæŶåĢĻ
    -0.08
    /apache
    -0.08
    POSITIVE LOGITS
    ì§ĵ
    0.09
    éĴĪ对
    0.09
    -muted
    0.09
    æ¢Ĩ
    0.09
    樱
    0.08
    éĵŃè®°
    0.08
    ìłģìľ¼ë¡ľ
    0.08
    zu
    0.08
    ä½ĵçİ°åľ¨
    0.08
    åĢĴåħ¥
    0.08
    Activations Density 0.027%

    No Known Activations