© 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. 40032
    Prev
    Next
    INDEX
    Explanations

    fans of

    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
     latter
    -0.10
    ä¸Ģæīĭ
    -0.10
    çĦ¶æĺ¯
    -0.10
    жи
    -0.09
    ä½ĵåĨħ
    -0.09
    è§Ĩ线
    -0.09
    æĪĺçķ¥æĢ§
    -0.08
    主è¦ģ
    -0.08
    梦è§ģ
    -0.08
    水管
    -0.08
    POSITIVE LOGITS
    串
    0.09
    æĭ±
    0.09
    onet
    0.08
    å°½æĹ©
    0.08
    ðŁĺį
    0.08
    èĢĥãģĪæĸ¹
    0.08
    äºĭä¸ļ
    0.08
    .reporting
    0.08
    ä¸įæĸŃå¢ŀåĬł
    0.08
    éĴī
    0.08
    Activations Density 0.012%

    No Known Activations