© 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. 10361
    Prev
    Next
    INDEX
    Explanations

    winning or leading

    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
    etta
    -0.11
    éĥ½åĸľæ¬¢
    -0.10
    è·ijäºĨ
    -0.10
    .Run
    -0.09
    æĪ´çĿĢ
    -0.09
    è¿Ŀæ³ķè¿Ŀè§Ħ
    -0.09
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    isol
    -0.08
    run
    -0.08
    æĸ½èĤ¥
    -0.08
    POSITIVE LOGITS
     uf
    0.09
    罨
    0.09
    æĢ¥äºİ
    0.09
    æ±Łä¸ľ
    0.08
    ç§ĭåŃ£
    0.08
    _uc
    0.08
    ä»Ģä¹Īäºĭ
    0.08
    ç¯Ŀ
    0.08
     searchText
    0.08
    讫
    0.08
    Activations Density 0.047%

    No Known Activations