© 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. 3241
    Prev
    Next
    INDEX
    Explanations

    honorable

    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
    åĻİ
    -0.09
    éĺ¶å±Ĥ
    -0.09
    arella
    -0.08
    rov
    -0.08
    ns
    -0.08
    ä½ĵè´¨
    -0.08
    aday
    -0.08
     liability
    -0.08
     Cair
    -0.08
    éĿĵ
    -0.08
    POSITIVE LOGITS
    为ä¹ĭ
    0.11
    深深çļĦ
    0.11
    ç´łé£Ł
    0.10
    æ³Ħæ¼ı
    0.10
    æ±ģ
    0.10
    ãģª
    0.09
    æĹłçŁ¥
    0.09
    èĬ·
    0.09
    ç¿¥
    0.09
    éŀĺ
    0.09
    Activations Density 0.009%

    No Known Activations