© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7909
    Prev
    Next
    INDEX
    Explanations

    even if

    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
    佬
    -0.11
    æĸ°ä¸ī
    -0.10
    åIJĪéĢĤçļĦ
    -0.10
    å¦Ĥæŀľæĺ¯
    -0.09
    æĹ¢çĦ¶
    -0.09
    å¦Ĥæŀľä¸į
    -0.09
    åħ¹
    -0.09
     ë§Įìķ½
    -0.09
    unks
    -0.09
    主è¦ģæľī
    -0.09
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.10
    åĩłæŃ¥
    0.09
    åIJįä¹ī
    0.09
    æĺ¯ä¸ºäºĨ
    0.09
     bureaucr
    0.09
    åĩĮ
    0.09
    ted
    0.09
    verständlich
    0.08
    åıªæĺ¯
    0.08
    çİ°å®ŀä¸Ń
    0.08
    Activations Density 0.011%

    No Known Activations