© 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. 63833
    Prev
    Next
    INDEX
    Explanations

    python library

    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
    åIJĦè¡Į
    -0.10
    粪
    -0.09
    PING
    -0.09
    éĽĩä½£
    -0.09
    éŀħ
    -0.09
     Rene
    -0.08
    Insn
    -0.08
    isz
    -0.08
    请éĹ®
    -0.08
     Peaks
    -0.08
    POSITIVE LOGITS
    iese
    0.09
    ä¹Łæľī
    0.09
    pyx
    0.09
     betr
    0.09
    éĤ¸
    0.09
    lyn
    0.08
    æĢ¨
    0.08
    æ¸ħåįİ
    0.08
    çģµæ°Ķ
    0.08
    ses
    0.08
    Activations Density 0.001%

    No Known Activations