© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    scrolling, map, screen, page, load

    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
    æİ¥åıĹäºĨ
    -0.10
    è®®
    -0.09
    çļĦç¼ĺ
    -0.09
    éĨĴ
    -0.09
    é¼IJ
    -0.09
    èŃ°
    -0.09
    outil
    -0.09
    é½ij
    -0.09
    AMPLE
    -0.09
    _WIN
    -0.08
    POSITIVE LOGITS
    å¼ĢéĺĶ
    0.11
     environments
    0.09
    åľ°è²Į
    0.08
    å±IJ
    0.08
    èĥĮæĻ¯
    0.08
    2
    0.08
    ç»Ļ大家
    0.08
    tog
    0.08
    1
    0.08
    é«ĺ空
    0.08
    Activations Density 0.201%

    No Known Activations