© 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. 10868
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
    éģIJ
    -0.10
     zwar
    -0.10
    çľ¼æ³ª
    -0.10
    èĥĦ
    -0.10
     Stateless
    -0.09
    GED
    -0.09
    çļĦçľ¼
    -0.09
    åħļé£İ
    -0.09
    ç¥
    -0.09
    éĥİ
    -0.09
    POSITIVE LOGITS
    è¿ĺè¦ģ
    0.12
    åĨįåĬłä¸Ĭ
    0.10
    éĤĦè¦ģ
    0.09
    è¿ĺæľīä¸Ģ个
    0.09
    åĬłä¸Ĭ
    0.09
    éĻĦåĬł
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
    åIJİéĿ¢çļĦ
    0.08
    æľĢè¿ij
    0.08
     Schneider
    0.08
    Activations Density 0.029%

    No Known Activations