© 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. 53335
    Prev
    Next
    INDEX
    Explanations

    negative adjectives followed by prepositions/auxiliaries

    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¸į说
    -0.11
    ä¸įåĪ°
    -0.11
    ä¸įå¾Ĺå·²
    -0.10
    autoload
    -0.09
    âļĶ
    -0.09
    弩
    -0.09
    æ·¡
    -0.09
    .pb
    -0.09
    éĵ
    -0.09
     nichts
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.13
     nor
    0.13
    åĽłåľ°
    0.10
    æĮ¨
    0.09
     whatsoever
    0.09
    åľ¨ç½ij绾
    0.09
    ä¹Łä¸įæĺ¯
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.08
    å¾Ĺ太
    0.08
    åĽĬ
    0.08
    Activations Density 0.119%

    No Known Activations