© 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. 36737
    Prev
    Next
    INDEX
    Explanations

    simple steps, time to take

    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
    滥çĶ¨
    -0.09
    æ¸İ
    -0.08
    çĨ
    -0.08
    ä¸Ģç»Ħ
    -0.08
    ç»ĻæĤ¨
    -0.08
    å§ij
    -0.08
     Nut
    -0.08
    æ®ļ
    -0.08
    èIJ¥åħ»
    -0.08
     coverage
    -0.08
    POSITIVE LOGITS
    åģļèµ·
    0.12
    å¾Īç®Ģåįķ
    0.12
    åģļä¸ĢäºĽ
    0.11
    åľ¨å®¶éĩĮ
    0.11
    æĹ¥å¸¸çĶŁæ´»
    0.11
    çĶŁæ´»æĸ¹å¼ı
    0.11
    æĹ¥å¸¸
    0.10
    åľ¨çĶŁæ´»ä¸Ń
    0.10
    æݪæĸ½
    0.09
     practices
    0.09
    Activations Density 0.062%

    No Known Activations