© 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. 12085
    Prev
    Next
    INDEX
    Explanations

    going beyond or far

    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
    çijĦ
    -0.10
    åĨįçİ°
    -0.10
    uxe
    -0.10
    èľĺèĽĽ
    -0.09
    amic
    -0.09
    ç´§å¼ł
    -0.09
    éĢĴ交
    -0.09
     ÑģобÑĢан
    -0.09
    æĹĹ
    -0.09
    漪
    -0.08
    POSITIVE LOGITS
    管çIJĨåijĺ
    0.09
    ÄĻż
    0.09
    ä¸įæŃ¢
    0.09
    éĻIJ度
    0.09
    ØŃرÙģ
    0.08
    æıIJ款
    0.08
    .espresso
    0.08
    omba
    0.08
    å°ıå¿ĥ
    0.08
    è¿ij
    0.08
    Activations Density 0.024%

    No Known Activations