© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    scores and statistics

    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
     пом
    -0.09
    olen
    -0.08
    orde
    -0.08
    æĸ¯åŁº
    -0.08
    ä¿Ŀåģ¥
    -0.08
    gee
    -0.08
    oop
    -0.08
    _bulk
    -0.08
     Bulk
    -0.07
    éºŁ
    -0.07
    POSITIVE LOGITS
    ç¾İèģĶ
    0.09
    çĶŁäº§æĢ»
    0.09
    è²łãģij
    0.09
    åīįä¸ĸ
    0.09
    åĨľåī¯
    0.09
    åħ¥ãĤĬ
    0.09
     ÐŁÑĢе
    0.09
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    /hash
    0.08
    ä¸İæŶ
    0.08
    Activations Density 0.068%

    No Known Activations