© 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. 34194
    Prev
    Next
    INDEX
    Explanations

    doesn't followed by verb

    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
    讳
    -0.10
    èĥ½å¤Ł
    -0.09
    éĵ¶
    -0.09
     Fah
    -0.08
    .au
    -0.08
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    éĥ½èĥ½å¤Ł
    -0.08
    ç»ıèIJ¥
    -0.08
    纯æ´ģ
    -0.08
    çļĦä¸Ģç§į
    -0.08
    POSITIVE LOGITS
    OF
    0.09
    å¾Ĵå¼Ł
    0.09
    æ¯ĶåĪ©
    0.09
    æĪijçľĭ
    0.08
    SCAN
    0.08
    ä¸įæĪIJ
    0.08
    oden
    0.08
    ä»İæł¹æľ¬ä¸Ĭ
    0.08
    _attached
    0.08
    åĿı
    0.08
    Activations Density 0.063%

    No Known Activations