© 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. 29411
    Prev
    Next
    INDEX
    Explanations

    quote

    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
    ules
    -0.10
    acz
    -0.10
    itel
    -0.10
    èĪģ
    -0.09
    çĿĢçľ¼
    -0.09
    /***/
    -0.09
    reur
    -0.09
    rian
    -0.09
    usk
    -0.08
    .Fprintf
    -0.08
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.09
    婵
    0.09
     Associ
    0.08
    æŀĭ
    0.08
    æĽ´å¤ļçļĦæĺ¯
    0.08
    å½ĵåľ°
    0.08
    ãģįãģŁ
    0.08
    äºĽä»Ģä¹Ī
    0.08
    ENDED
    0.08
     лиÑĪÑĮ
    0.08
    Activations Density 0.016%

    No Known Activations