© 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. 29383
    Prev
    Next
    INDEX
    Explanations

    Idaho County

    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
    ocked
    -0.11
    é½IJé²ģ
    -0.10
    æĮģä¹ħ
    -0.10
    å¾·å·ŀ
    -0.10
    æĪ¿ä¸ľ
    -0.10
    å±±ä¸ľçľģ
    -0.09
    å¨ģæµ·
    -0.09
    梵
    -0.09
    ADI
    -0.09
    è±¹
    -0.08
    POSITIVE LOGITS
     Spokane
    0.11
    çĵľ
    0.11
    çı¥
    0.11
    绵éĺ³
    0.10
    篾
    0.10
    ç¾Į
    0.10
    åºĵéĩĮ
    0.10
    çī¦
    0.09
    éĿĴæµ·çľģ
    0.09
    涪
    0.09
    Activations Density 0.103%

    No Known Activations