© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37287
    Prev
    Next
    INDEX
    Explanations

    continuous education and development

    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
    ä¹ħä¹ħ
    -0.10
    åĨįä¹Łä¸į
    -0.10
    ä¸įåĨį
    -0.10
    è¿Łè¿Ł
    -0.09
     Calder
    -0.09
     Cald
    -0.08
    èĢĥ
    -0.08
    LV
    -0.08
    ç§įç§į
    -0.08
    closed
    -0.08
    POSITIVE LOGITS
    åķ¬
    0.13
    æĶ¹è¿Ľ
    0.10
    æĶ¹åĸĦ
    0.10
    æĶ¹éĿ©åĪĽæĸ°
    0.10
    寻æ±Ĥ
    0.10
     improvement
    0.09
    åįıä¼ļä¼ļåijĺ
    0.09
    积累
    0.09
    èĿİ
    0.09
    ä¸İæĹ¶ä¿±
    0.09
    Activations Density 0.057%

    No Known Activations