© 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. 16525
    Prev
    Next
    INDEX
    Explanations

    i.e. and x marks

    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
    Negative Logits
     Lips
    -0.09
    ags
    -0.09
    åĨ·åºĵ
    -0.08
    ä¸ĵ人
    -0.08
     Latter
    -0.08
     hè
    -0.08
    åħ¨å®¶
    -0.08
    æķĽ
    -0.08
    åIJĦèĩªçļĦ
    -0.08
     Sle
    -0.08
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.10
    éĻĮ
    0.09
    们
    0.09
    swers
    0.09
    åľ¨è·¯ä¸Ĭ
    0.08
    éĴĨ
    0.08
     лид
    0.08
    tingham
    0.08
    åħij
    0.08
     gy
    0.08
    Activations Density 0.100%

    No Known Activations