© 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. 29981
    Prev
    Next
    INDEX
    Explanations

    clambake mystery, pity party, futon-a-thon, treasure hunt, posting spree

    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
    æľīèĩªå·±çļĦ
    -0.09
    æ²®
    -0.09
    umont
    -0.08
    æ
    -0.08
    ullah
    -0.08
    _EC
    -0.08
    ern
    -0.08
    .gold
    -0.08
    _Api
    -0.08
     rot
    -0.08
    POSITIVE LOGITS
     ÑģоÑģÑĤо
    0.10
     пÑĢоиÑģÑħодиÑĤ
    0.09
    ç¿»å¼Ģ
    0.09
    ç»ĵæĿŁäºĨ
    0.09
    è¿ĩåIJİ
    0.09
    ç»ĵæĿŁåIJİ
    0.09
    ä¼ļéķ¿
    0.09
    çĶ¨äººåįķä½į
    0.08
    åĴª
    0.08
    åıijçĶŁåľ¨
    0.08
    Activations Density 0.086%

    No Known Activations