© 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. 47923
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    éĻĨç»Ń
    -0.09
    建åĨĽ
    -0.08
    itters
    -0.08
    plus
    -0.08
    ous
    -0.08
    嵬
    -0.08
    åĪ°æĿ¥
    -0.08
    æĿ¥ä¸´
    -0.08
    çħ§æł·
    -0.08
    æ£ĺ
    -0.08
    POSITIVE LOGITS
    gia
    0.10
    æĤ¨çļĦ
    0.10
    oha
    0.10
    æīĢè¿°
    0.10
    å¸ĮæľĽ
    0.09
    æŁ¥æĺİ
    0.09
    cob
    0.09
     glfw
    0.09
     Yên
    0.09
     Levin
    0.09
    Activations Density 0.137%

    No Known Activations