© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    Website, Joint, Health, Dam, Archive, strateg, Ad, winter

    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
    ä»İä¸Ń
    -0.09
    çIJIJ
    -0.09
    Csv
    -0.08
    è¿ŀç»Ń
    -0.08
    rophy
    -0.08
    abet
    -0.08
    è¸ŀ
    -0.07
     Ùħع
    -0.07
    衾
    -0.07
    dig
    -0.07
    POSITIVE LOGITS
     Rubber
    0.09
    ataka
    0.09
    æ©¡èĥ¶
    0.09
    _gs
    0.09
    holder
    0.09
     rubber
    0.09
    LEC
    0.09
    ä¸ĢèĦļ
    0.09
    ObjectContext
    0.09
    æĽ´éĩįè¦ģ
    0.09
    Activations Density 0.209%

    No Known Activations