© 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. 23550
    Prev
    Next
    INDEX
    Explanations

    find more about

    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
    idy
    -0.10
    æĺ¯åĽ½åĨħ
    -0.10
    OTS
    -0.09
    å¤įæŁ¥
    -0.09
    ç»´æĿĥ
    -0.09
    ãģ¨ãģĨ
    -0.09
     мом
    -0.08
    顾
    -0.08
    _MAGIC
    -0.08
    äºĨ好åĩł
    -0.08
    POSITIVE LOGITS
    è·ijäºĨ
    0.09
    æł¸éħ¸
    0.08
    ä¼ĺ
    0.08
    ä¸ĢåĪ»
    0.08
    ä¸ĭä¸Ģ
    0.08
    iska
    0.08
    æıIJè®®
    0.08
     Gül
    0.08
    æį®
    0.08
     exclusive
    0.08
    Activations Density 0.021%

    No Known Activations