© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16910
    Prev
    Next
    INDEX
    Explanations

    boys and girls sports

    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
    æ¦ķ
    -0.11
    pping
    -0.09
    èĪĮ
    -0.09
    亲身
    -0.09
    æ³±
    -0.09
    被æī§è¡Į
    -0.09
    stract
    -0.09
    оваÑĢ
    -0.09
    wargs
    -0.08
    chooser
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.11
    ä¸ĢçĤ¹åĦ¿
    0.10
    泯
    0.09
    ourced
    0.09
    pire
    0.09
    æ¯ı人
    0.09
    ä¸ĢçĤ¹
    0.09
    realm
    0.09
    楼å±Ĥ
    0.09
    ðŁı½
    0.09
    Activations Density 0.013%

    No Known Activations