© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35823
    Prev
    Next
    INDEX
    Explanations

    communication and correspondence

    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
    ocy
    -0.08
     Tate
    -0.08
    éļĨ
    -0.08
    åIJĮæĥħ
    -0.08
    пов
    -0.08
     bachelor
    -0.08
     Petr
    -0.08
    人家
    -0.08
    éĢļ
    -0.07
    ç»ıéªĮåĴĮ
    -0.07
    POSITIVE LOGITS
    indre
    0.11
    BOR
    0.11
    åĵģå¾·
    0.10
    ä¸Ģå°ģ
    0.10
    enson
    0.10
    èĪī
    0.10
    çļĦä¸ĢéĿ¢
    0.09
    åĶ®åIJİ
    0.09
    ãĥ³ãĤ°
    0.09
     اÙĦÙħص
    0.09
    Activations Density 0.034%

    No Known Activations