© 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. 20537
    Prev
    Next
    INDEX
    Explanations

    from [organization/source]

    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
    éĤ£æł·çļĦ
    -0.10
    æĮ¹
    -0.10
    ä¸ĢåĪĢ
    -0.10
    emento
    -0.10
    车éĺŁ
    -0.09
    èij³
    -0.09
    ingu
    -0.09
    éĤ£éº¼
    -0.09
    åIJijä¸ĭ
    -0.09
    dorf
    -0.08
    POSITIVE LOGITS
    åĽĽçº§
    0.09
    ованиÑı
    0.08
    åѤ
    0.08
    ä¸įä½Ĩ
    0.08
    é«ĺåľ°
    0.08
     purs
    0.08
     Extras
    0.08
    ä¸İåħ¶
    0.08
     bó
    0.08
    headed
    0.08
    Activations Density 0.131%

    No Known Activations