© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20569
    Prev
    Next
    INDEX
    Explanations

    got to know

    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
    hardt
    -0.10
    æĥ³ä¸įåĪ°
    -0.10
    åĽ½åĬ¡
    -0.09
    åĮłå¿ĥ
    -0.09
    çĻ½é¢Ĩ
    -0.09
    èĪ«
    -0.09
     Gamer
    -0.09
    indsay
    -0.08
    ulet
    -0.08
    enie
    -0.08
    POSITIVE LOGITS
    身边çļĦ
    0.09
    ings
    0.09
    æĪĸå¤ļ
    0.08
    æīĭä¸ŃçļĦ
    0.08
    INGS
    0.08
    èĮ¬
    0.08
    ãģĮãĤī
    0.08
    为æŃ¢
    0.08
    æ£Ģå¯Łæľºåħ³
    0.08
    sert
    0.08
    Activations Density 0.003%

    No Known Activations