© 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. 815
    Prev
    Next
    INDEX
    Explanations

    motion verbs

    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
    odel
    -0.09
    äºĭåħ³
    -0.09
    çijľ
    -0.09
    åĺ±
    -0.09
     thừa
    -0.08
    share
    -0.08
    çŃł
    -0.08
    å¼
    -0.08
    mani
    -0.08
    æ¢ĵ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个人
    0.10
    æ·ĭ
    0.10
    æ¯ıä¸Ģ个人
    0.09
    fade
    0.09
    .mutex
    0.09
    çªĴ
    0.09
    æľ¬éĩij
    0.09
    _BREAK
    0.09
    afen
    0.09
    vell
    0.09
    Activations Density 0.073%

    No Known Activations