© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    new updates and content

    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
    æ¯Ķäºļ
    -0.10
    onz
    -0.09
    æŃī
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    éĢĶ
    -0.09
    çĴľ
    -0.09
    gard
    -0.08
    æĮ¨
    -0.08
    éĿ©æĸ°
    -0.08
    _INS
    -0.08
    POSITIVE LOGITS
    åľ¨æİ¥åıĹ
    0.09
    immel
    0.09
    å¹ķå¢Ļ
    0.09
    makt
    0.09
    èµŃ
    0.09
    éļIJèĶ½
    0.09
    ocale
    0.08
     báºŃt
    0.08
    齿
    0.08
    æĢĿ
    0.08
    Activations Density 0.005%

    No Known Activations