© 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. 10770
    Prev
    Next
    INDEX
    Explanations

    record for hottest years

    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
    æĪ´ä¸Ĭ
    -0.11
    æĪ´
    -0.09
    ä¹Łèĥ½
    -0.09
    åİķæīĢ
    -0.09
    ÑĥÑģÑĤ
    -0.09
    æ½Ķ
    -0.09
    æĪ·ç±į
    -0.09
    ä¸ĢåıĮ
    -0.09
    ä¸Ģ身
    -0.09
    ãģ´
    -0.09
    POSITIVE LOGITS
     Cres
    0.09
    æ¾İ
    0.09
    æŃ¢ãĤģ
    0.09
    æijĦ
    0.09
    ogh
    0.08
    çĽ¯
    0.08
    èĩĮ
    0.08
    é¼ĵ
    0.08
    åĴİ
    0.08
     lag
    0.08
    Activations Density 0.025%

    No Known Activations