© 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. 48465
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    å¤Ł
    -0.09
    èĽ±
    -0.08
    èIJ¥
    -0.08
    è´·
    -0.08
    æµİ
    -0.08
    对èĩªå·±çļĦ
    -0.08
    欤
    -0.08
     Yankee
    -0.08
    åĪ°ä½į
    -0.08
    ãģªãģĮãĤī
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.12
     inclusive
    0.12
    åĨįåĪ°
    0.11
    éĥ½éĿŀ常
    0.10
     arasındaki
    0.10
    clusive
    0.10
    éĥ½å¾Ī
    0.10
    éĥ½åľ¨
    0.10
     aras
    0.09
    ä¹ĭéĹ´
    0.09
    Activations Density 0.294%

    No Known Activations