© 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. 12111
    Prev
    Next
    INDEX
    Explanations

    give me a break

    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
    apolis
    -0.09
    æ°´æĻ¶
    -0.08
    ä¸įåIJĮç¨ĭ度
    -0.08
    èħ°
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    è¯
    -0.08
    ual
    -0.08
    atre
    -0.08
    å¾Ģå¹´
    -0.08
    çļĦåħ·ä½ĵ
    -0.08
    POSITIVE LOGITS
    itives
    0.10
    èģĮ
    0.10
    çijĽ
    0.10
    ä¸įè¦ģ
    0.09
    çĪ±äºº
    0.09
    è¿Īåĩº
    0.09
    ä¸įçĦ¶
    0.09
    ä¸įè¦ģ太
    0.08
    FragmentManager
    0.08
    .updateDynamic
    0.08
    Activations Density 0.003%

    No Known Activations