© 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. 36596
    Prev
    Next
    INDEX
    Explanations

    incident reports and complaints

    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
    æĪijè§īå¾Ĺ
    -0.10
    åºĦ严
    -0.09
    оÑĢа
    -0.09
    æĹłæĥħ
    -0.09
    çµ
    -0.08
    æĪijåĸľæ¬¢
    -0.08
     мо
    -0.08
    ä¼ĹæīĢ
    -0.08
    纤
    -0.08
    帮æĪij
    -0.08
    POSITIVE LOGITS
    举æĬ¥
    0.10
    æĬķè¯ī
    0.10
     concerns
    0.10
    æĬ¥æ¡Ī
    0.09
    æ¶Īæģ¯ç§°
    0.09
    esthetic
    0.09
    å½ĵæŶçļĦ
    0.09
    æ¯Ķéĩį
    0.09
     complaints
    0.09
    ìĭ¤
    0.09
    Activations Density 0.037%

    No Known Activations