© 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. 12155
    Prev
    Next
    INDEX
    Explanations

    code, lyrics, or specific formats

    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
    èĥ¥
    -0.10
    æĺİæĺİ
    -0.10
    ç¢Į
    -0.09
    æķ£
    -0.09
    bose
    -0.09
    ç³ħ
    -0.08
    æ½®
    -0.08
    istra
    -0.08
    çŁ¥æĥħ
    -0.08
    cloud
    -0.08
    POSITIVE LOGITS
    åºł
    0.10
    -ing
    0.09
    èħł
    0.09
    AQ
    0.09
    Bias
    0.09
    âŀ¥
    0.09
    áĥ
    0.08
    ä¸İåIJ¦
    0.08
    åıijçĹħçİĩ
    0.08
    å¦ĥ
    0.08
    Activations Density 0.001%

    No Known Activations