© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63532
    Prev
    Next
    INDEX
    Explanations

    Forbes, magazine, and wealth rankings

    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
    åį±
    -0.10
    itr
    -0.09
    reich
    -0.09
    etus
    -0.09
    _ring
    -0.08
    abbrev
    -0.08
     gsi
    -0.08
    ucher
    -0.08
    oi
    -0.08
    رش
    -0.08
    POSITIVE LOGITS
    深度èŀįåIJĪ
    0.10
    èIJ¥
    0.09
    æĹłåı¯
    0.09
    æĺİçĻ½
    0.09
    åŃIJå¼Ł
    0.09
    çĽĺ
    0.08
    æĹłç§ģ
    0.08
    éĻIJæŶ
    0.08
    ies
    0.08
    å°ĸ
    0.08
    Activations Density 0.001%

    No Known Activations