© 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. 54558
    Prev
    Next
    INDEX
    Explanations

    help of

    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
    è¢Ĥ
    -0.10
    å·¡èĪª
    -0.09
    æĬ¤èĤ¤
    -0.09
    人æĿĥ
    -0.09
    仪
    -0.08
    è¾ij
    -0.08
    iesel
    -0.08
     Wich
    -0.08
    éĥ½ä¸įæķ¢
    -0.08
    wayne
    -0.08
    POSITIVE LOGITS
    å¼Ģåĩº
    0.11
     Balk
    0.10
    ç»Ī端
    0.08
    สรร
    0.08
    å®ĥåı¯ä»¥
    0.08
    lessness
    0.08
     means
    0.08
     Äijỡ
    0.08
    åĬ©æīĭ
    0.08
    .Helper
    0.08
    Activations Density 0.027%

    No Known Activations