© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6104
    Prev
    Next
    INDEX
    Explanations

    for me

    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
    Negative Logits
    éĨĴ
    -0.08
    åIJĪéĢĤçļĦ
    -0.08
    @g
    -0.08
    åı£ä¸Ń
    -0.08
    é£İæļ´
    -0.08
    âĻĤ
    -0.08
    edList
    -0.08
    REW
    -0.08
    osex
    -0.08
    ä¸įåĨįæĺ¯
    -0.08
    POSITIVE LOGITS
    æĮijåīĶ
    0.10
    好äºĭ
    0.10
    >{@
    0.10
    èĴ
    0.10
    éĹ¾
    0.09
    婵
    0.09
    ange
    0.09
    orate
    0.08
    itches
    0.08
    æ¢Ń
    0.08
    Activations Density 0.009%

    No Known Activations