© 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. 51594
    Prev
    Next
    INDEX
    Explanations

    writing and acting quality

    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
    宿
    -0.09
    æľ«
    -0.09
    è²
    -0.09
    ç¼ī
    -0.09
    åŀĽ
    -0.09
    ä¸ĥ大
    -0.08
    çļĦ羣å®ŀæĢ§
    -0.08
    .yahoo
    -0.08
    æļ§
    -0.08
    á»ķi
    -0.08
    POSITIVE LOGITS
    èµı
    0.11
    è´¨éĩı
    0.11
    è´¨éĩıåĴĮ
    0.10
     quality
    0.09
    質éĩı
    0.09
     craftsmanship
    0.09
    è³ŀ
    0.09
    ej
    0.09
    æijĦå½±
    0.09
    çļĦè´¨éĩı
    0.08
    Activations Density 0.071%

    No Known Activations