© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12143
    Prev
    Next
    INDEX
    Explanations

    that [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
    è½½ä½ĵ
    -0.09
    ä¸įå¾Ĺä¸į
    -0.09
    åºĶåıĬæŶ
    -0.09
    ambi
    -0.09
    avery
    -0.09
     Blob
    -0.08
    ä¸įå¾Ĺå·²
    -0.08
    _locator
    -0.08
    åĨĻäºĨ
    -0.08
    CustomLabel
    -0.08
    POSITIVE LOGITS
    涵çĽĸ
    0.12
    æĹ¢èĥ½
    0.12
    åħ¼é¡¾
    0.10
    è·
    0.09
    æĢ§ä»·æ¯Ķ
    0.09
    åĪĩ
    0.09
    çļĦ人éĥ½
    0.09
    缴å±ŀ
    0.09
    满足
    0.08
    满
    0.08
    Activations Density 0.108%

    No Known Activations