© 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. 48494
    Prev
    Next
    INDEX
    Explanations

    pain or nuisance

    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
    åī½
    -0.10
    åīįæīĢ
    -0.09
     pharm
    -0.09
    åĶĶ
    -0.09
    究
    -0.09
    æŃ£éĿ¢
    -0.09
    åľ°æłĩ
    -0.09
    itori
    -0.08
    檬
    -0.08
    è²Į
    -0.08
    POSITIVE LOGITS
    麻çĥ¦
    0.11
     dream
    0.09
    åįģ足
    0.09
    æģ¶å¿ĥ
    0.09
    头çĸ¼
    0.08
    为客æĪ·
    0.08
    è´¹
    0.08
    åįł
    0.08
    ìĤ¬íķŃ
    0.08
    ingham
    0.08
    Activations Density 0.011%

    No Known Activations