© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    severity and intensity

    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
    бÑĭ
    -0.10
    воÑĢ
    -0.10
    é²į
    -0.09
    spr
    -0.09
    pson
    -0.09
    bing
    -0.09
     Bale
    -0.08
     Marble
    -0.08
    ski
    -0.08
    -et
    -0.08
    POSITIVE LOGITS
    ç¨ĭ度
    0.13
    度
    0.13
    è¶Ĭé«ĺ
    0.10
     levels
    0.10
    åı¯æĥ³èĢĮçŁ¥
    0.10
    ä¸Ģå®ļç¨ĭ度
    0.09
    çļĦç¨ĭ度
    0.09
    åįģ足
    0.09
    ç¥Ŀ
    0.09
    åıĸåĨ³äºİ
    0.09
    Activations Density 0.209%

    No Known Activations