© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    division multiple access

    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¸ĭåįĬ
    -0.09
    æ¥ŀ
    -0.09
    æľºæŀĦ
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    åĴ±
    -0.09
    æ¯Ļ
    -0.09
    amazon
    -0.08
    æĺ¯éĿŀ
    -0.08
     CE
    -0.08
    å´ĩ
    -0.08
    POSITIVE LOGITS
    åıijå±ķ空éĹ´
    0.10
    ç¬Ļ
    0.10
    _allocated
    0.09
    å¹»æĥ³
    0.09
    ãĤ¢ãĥĥãĥĹ
    0.09
    èĮİ
    0.09
    ä¸ĢåĿĹ
    0.09
    adoo
    0.09
    quist
    0.09
     Berger
    0.09
    Activations Density 0.201%

    No Known Activations