© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52249
    Prev
    Next
    INDEX
    Explanations

    abnormalities or dysregulation

    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
    æ¯ķ竣
    -0.11
     Baths
    -0.10
    æŃ¤ä¸¾
    -0.09
    ãĤİ
    -0.09
    ç²²
    -0.09
    çĥŃéĹ¹
    -0.09
    alytics
    -0.09
    ç»ĻæĤ¨
    -0.08
    ä¸İä¼Ĺ
    -0.08
     Bender
    -0.08
    POSITIVE LOGITS
    失è°ĥ
    0.09
    æĵį纵
    0.09
    å®ĥåı¯ä»¥
    0.09
    çļĦéĩįè¦ģæĢ§
    0.09
     Manip
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    å¼Ħ
    0.08
    çĵ¢
    0.08
    ogh
    0.08
    _relation
    0.08
    Activations Density 0.762%

    No Known Activations