© 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. 63136
    Prev
    Next
    INDEX
    Explanations

    in contrast to

    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
    çīĮ
    -0.09
    ihar
    -0.09
    æ¯ħ
    -0.09
    æĪļ
    -0.09
    寰
    -0.08
    aneous
    -0.08
    ä¸ĭåıij
    -0.08
    2
    -0.08
     Pey
    -0.08
    éĽ³
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.11
    ä»»ä½ķæŶåĢĻ
    0.10
    éĤ£æł·
    0.10
    èĭįçĻ½
    0.10
    åģļæ³ķ
    0.10
    æ¯ı次éĥ½
    0.09
    çļĦåģļæ³ķ
    0.09
    éķ¿ä¹ħ
    0.09
    ä¸Ģåij³
    0.09
    æĸĩåĮĸ建设
    0.09
    Activations Density 0.087%

    No Known Activations