© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    time of year

    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
    elman
    -0.10
    æĺķ
    -0.09
    éĤ£ä¸Ģ天
    -0.09
    们çļĦ
    -0.09
    æĹłç©·
    -0.09
    ãģ½
    -0.08
    们
    -0.08
    éĴĬ
    -0.08
    ITU
    -0.08
    èĥ§
    -0.08
    POSITIVE LOGITS
    beit
    0.09
    èĢģ大
    0.08
    igo
    0.08
    çĶŁäº§æĢ»åĢ¼
    0.08
    uler
    0.08
    abouts
    0.08
    åŃ£èĬĤ
    0.08
    ä¹ŁæŃ£æĺ¯
    0.08
    /month
    0.08
    ulers
    0.07
    Activations Density 0.010%

    No Known Activations