© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    excluding the path

    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
    OWN
    -0.10
    ä¸įåľ¨ä¹İ
    -0.10
    æĪŁ
    -0.09
    ways
    -0.09
    åIJĮæł·çļĦ
    -0.09
    ookie
    -0.08
    é£İçŃĿ
    -0.08
     Gig
    -0.08
    çĭł
    -0.08
    oodles
    -0.08
    POSITIVE LOGITS
    çIJĨä¼ļ
    0.10
    çĽ²çĽ®
    0.10
    .ret
    0.10
    éĹ®éĹ®
    0.10
    çIJĨ
    0.09
    åIJİéĿ¢çļĦ
    0.09
    æijĺ
    0.09
    uku
    0.09
    使ä¹ĭ
    0.09
    æİī
    0.09
    Activations Density 0.084%

    No Known Activations