© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36342
    Prev
    Next
    INDEX
    Explanations

    uppity, up, ups

    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
    äºĶå®ĺ
    -0.09
    atti
    -0.09
    asher
    -0.09
     scrollTop
    -0.09
    è¾Ĭ
    -0.09
     Blasio
    -0.09
    msp
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    _UTF
    -0.08
     Ñĥказ
    -0.08
    POSITIVE LOGITS
    主æĦı
    0.10
    æĤ²
    0.10
    ãĤµãĥ¼
    0.09
    æĤ²åī§
    0.09
    åĮ¹
    0.09
    çİ®
    0.08
    åĩĦ
    0.08
     дела
    0.08
    æĿŀ
    0.08
    å¯Ĥå¯ŀ
    0.08
    Activations Density 0.004%

    No Known Activations