© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22323
    Prev
    Next
    INDEX
    Explanations

    for everyone or suit

    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
    æľ¬èº«å°±æĺ¯
    -0.09
    äºĮèĢħ
    -0.09
    è½»
    -0.09
    oir
    -0.08
     TBD
    -0.08
    lux
    -0.08
    ç®ĹäºĨ
    -0.08
     forts
    -0.08
    awe
    -0.08
    çī
    -0.08
    POSITIVE LOGITS
    æĢ»æľī
    0.11
    èĥ½æ»¡è¶³
    0.11
    éĿ¢åIJij
    0.11
    éĥ½æľīèĩªå·±
    0.10
    aille
    0.10
    å½ĵä¹ĭæĹłæĦ§
    0.10
     اÙĦجÙħÙĬع
    0.10
    ä¾Ľ
    0.10
     Ø´ÙĬØ¡
    0.09
    æ¯ı个人
    0.09
    Activations Density 0.056%

    No Known Activations