© 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. 11331
    Prev
    Next
    INDEX
    Explanations

    parts and components

    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
    åħ¬çĽĬæĢ§
    -0.10
    NESS
    -0.10
    èŀ¯
    -0.09
    äºĮ次
    -0.09
    _tac
    -0.09
     WARN
    -0.09
    è´ª
    -0.09
    æĿ¥å½¢å®¹
    -0.08
    æ°°
    -0.08
    alker
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶ä»ĸ
    0.10
    çļĦ身影
    0.10
    راس
    0.09
    éĽĨä¸Ńåľ¨
    0.08
    çļĦèĦ¸
    0.08
    ingles
    0.08
     ÑĤам
    0.08
    çļĦéĤ£ä¸Ģ
    0.08
    åľ¨éĩĮéĿ¢
    0.08
    ä¹ĭç±»
    0.08
    Activations Density 0.738%

    No Known Activations