© 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. 11946
    Prev
    Next
    INDEX
    Explanations

    mathematics, setting, evolutionary, form, marketer, skin

    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
    人人éĥ½
    -0.11
    å¨ĵ
    -0.11
    ãĥĵãĤ¸ãĥį
    -0.10
    å¤ļä½Ļ
    -0.10
    èİ«åIJįåħ¶å¦Ļ
    -0.10
    æĪIJå°±æĦŁ
    -0.10
    ä¸Ģè·¯ä¸Ĭ
    -0.10
    ãģĬäºĴ
    -0.10
    çŀŃ解並
    -0.10
    æĹłè®ºæĺ¯
    -0.10
    POSITIVE LOGITS
    0.09
    4
    0.08
    3
    0.08
    7
    0.07
     grave
    0.07
    2
    0.07
    讦
    0.07
    1
    0.07
    6
    0.07
    5
    0.07
    Activations Density 1.400%

    No Known Activations