© 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. 20289
    Prev
    Next
    INDEX
    Explanations

    derogatory term

    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
    çĿ¦
    -0.08
    å²ĺ
    -0.08
    èĶ
    -0.08
    æĸ½èĤ¥
    -0.08
     simplex
    -0.07
    rozen
    -0.07
     rationale
    -0.07
     fooled
    -0.07
     flo
    -0.07
    èĻļå¼±
    -0.07
    POSITIVE LOGITS
    è¯ĥ
    0.12
    åIJ«ä¹ī
    0.12
    åģıåIJij
    0.12
    涵
    0.12
    è´ŁéĿ¢
    0.12
    æŃ£éĿ¢
    0.11
    éĻĦåĬł
    0.11
    ÑĢÑı
    0.10
    æľ¯è¯Ń
    0.10
    è´¬
    0.10
    Activations Density 0.064%

    No Known Activations