© 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. 21398
    Prev
    Next
    INDEX
    Explanations

    track towards a future

    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
    åİĨå¹´
    -0.12
    人èĦī
    -0.11
    èĮ«çĦ¶
    -0.10
    éĺ±
    -0.09
    æĢ»ä¼ļ
    -0.09
    arel
    -0.09
    å¸Ĥåľºç«ŀäºī
    -0.09
     Bien
    -0.08
    æĺİæĺ¾çļĦ
    -0.08
    æµĵæµĵçļĦ
    -0.08
    POSITIVE LOGITS
    çľĭæ¸ħ
    0.10
     redis
    0.10
     fut
    0.10
    æĪij们éľĢè¦ģ
    0.10
    æĽ´éĢĤåIJĪ
    0.09
    å·²ç»ıå¼Ģå§ĭ
    0.09
    æĸ°çļĦ
    0.09
    éĩįæĸ°
    0.09
    æĪij们åºĶ该
    0.09
    æľªæĿ¥
    0.08
    Activations Density 0.133%

    No Known Activations