© 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. 60631
    Prev
    Next
    INDEX
    Explanations

    suggestions and ideas

    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
     intensified
    -0.09
    aux
    -0.09
    éĥı
    -0.09
    订
    -0.09
     ASSIGN
    -0.08
    èĮŃ
    -0.08
     bay
    -0.08
     Ps
    -0.08
    éĩijå¥ĸ
    -0.08
    æľīéĻIJ责任
    -0.08
    POSITIVE LOGITS
    æıIJåĩº
    0.10
    æıIJè®®
    0.10
    çŃĸ
    0.09
     proposal
    0.09
    建议
    0.09
    åı¦æľī
    0.09
    ðŁĴ¡
    0.09
    举æݪ
    0.09
    建èŃ°
    0.08
    åı¦
    0.08
    Activations Density 0.026%

    No Known Activations