© 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. 47632
    Prev
    Next
    INDEX
    Explanations

    expresses reason or intent

    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
    Negative Logits
    mans
    -0.10
    å¤ļæķ°
    -0.09
    _helpers
    -0.08
     Nil
    -0.08
    ä½łåĸľæ¬¢
    -0.08
     Bros
    -0.08
    èĥ¸
    -0.08
     assorted
    -0.08
    Nil
    -0.08
    æݨèĸ¦
    -0.08
    POSITIVE LOGITS
    以便
    0.13
    åIJ¦åĪĻ
    0.11
    ä¸įçĦ¶
    0.11
     otherwise
    0.11
    以éĺ²
    0.10
    以åħį
    0.10
    ä»İä¸ļèĢħ
    0.09
    伺
    0.09
    æIJĶ
    0.09
    è¯įæĿ¡
    0.09
    Activations Density 0.682%

    No Known Activations