© 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. 31344
    Prev
    Next
    INDEX
    Explanations

    general + noun

    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
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.10
     Mond
    -0.09
    æ½ľ
    -0.08
    oulos
    -0.08
    好åIJ§
    -0.08
    gear
    -0.08
    è¡Ģ液循çݯ
    -0.08
    ategories
    -0.08
    ean
    -0.08
    éħįæĸĻ
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.12
    /general
    0.12
    -purpose
    0.11
    idades
    0.11
    ities
    0.11
    ä¾Ĩ說
    0.10
    ised
    0.10
    åĮĸçļĦ
    0.10
    ìłģìĿ¸
    0.10
    èĦ±
    0.10
    Activations Density 0.075%

    No Known Activations