© 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. 16905
    Prev
    Next
    INDEX
    Explanations

    stative verbs or adjectives

    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
    æŀ¶
    -0.10
    å¾Ģå¾Ģ
    -0.09
    好åĥı
    -0.09
    bare
    -0.09
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    -0.08
     кÑĢаÑģоÑĤ
    -0.08
    åħ³éĶ®
    -0.08
    å¢ħ
    -0.08
    åIJį声
    -0.08
    çIJIJ
    -0.08
    POSITIVE LOGITS
    åĩĨå¤ĩ好
    0.11
    æľĢéĢĤåIJĪ
    0.11
    åŁºè¾ħ
    0.10
    æĽ´éĢĤåIJĪ
    0.10
    ä¸į足以
    0.09
    该æĿij
    0.09
    å½ĵä¹ĭ
    0.09
    æľīè¶³å¤ŁçļĦ
    0.09
    éĢ®
    0.09
    æīĢéľĢ
    0.09
    Activations Density 0.047%

    No Known Activations