© 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. 33066
    Prev
    Next
    INDEX
    Explanations

    he and his/her

    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
    æĪijåĴĮ
    -0.10
    ä¸įç¦ģ
    -0.09
    rips
    -0.09
    å´½
    -0.09
    è·¨çķĮ
    -0.08
    èĢģ头
    -0.08
    é¢ĨåĨĽ
    -0.08
    天ä¸ĭ
    -0.08
    ä½łæĺ¯
    -0.08
    ÙĦت
    -0.08
    POSITIVE LOGITS
    ä¸Ģèµ·åİ»
    0.09
    å¼ĢæľĹ
    0.09
    ä¸Ĭåı¸
    0.09
    ниÑĨа
    0.09
    ä¸Ģ个
    0.09
    åıĬåħ¶
    0.09
    VERAGE
    0.08
    èĤ©è´Ł
    0.08
    ä¸Ģèµ·
    0.08
    æŃ¹
    0.08
    Activations Density 0.040%

    No Known Activations