© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9545
    Prev
    Next
    INDEX
    Explanations

    quality and suitability

    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
    èĩªå·±åĸľæ¬¢
    -0.10
    å±Ĥåĩºä¸įç©·
    -0.09
    è¿Ļç§įäºĭæĥħ
    -0.09
    ew
    -0.08
    éĻĭ
    -0.08
    红线
    -0.08
    羡
    -0.08
    eta
    -0.08
    ä¸įè´Ł
    -0.08
    isted
    -0.08
    POSITIVE LOGITS
    éĢĤåIJĪ
    0.20
    éĢĤçĶ¨äºİ
    0.19
    éĿŀ常éĢĤåIJĪ
    0.19
    æĽ´éĢĤåIJĪ
    0.13
    çĶ¨äºİ
    0.13
    éģ©åIJĪ
    0.13
    主è¦ģçĶ¨äºİ
    0.12
    åı¯çĶ¨äºİ
    0.12
    à¹Ģหมาะ
    0.12
    æľĢéĢĤåIJĪ
    0.12
    Activations Density 0.124%

    No Known Activations