© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10030
    Prev
    Next
    INDEX
    Explanations

    Unique, Holidays, Barrel, Basket

    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
    为主é¢ĺ
    -0.09
    该éĻ¢
    -0.09
    该åħ¬åı¸
    -0.09
    ItemType
    -0.09
    enson
    -0.08
     tess
    -0.08
    说æĺ¯
    -0.08
    æĮ
    -0.08
    为主é¢ĺçļĦ
    -0.08
     bankrupt
    -0.08
    POSITIVE LOGITS
    usher
    0.12
    å¸¦ä½ł
    0.11
    åħ¨èµĦ
    0.10
    æĹĹä¸ĭçļĦ
    0.10
    è¿Ļè¾¹
    0.10
     ÑģÑĤÑĢем
    0.10
    ç§ī
    0.10
    å§ĭç»Ī
    0.10
    æķ¢
    0.09
    ç»Ī身
    0.09
    Activations Density 0.089%

    No Known Activations