© 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. 6449
    Prev
    Next
    INDEX
    Explanations

    reasoning connectors

    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
    ä¸įå¾Ĺå·²
    -0.11
    åĢĴæĺ¯
    -0.08
    èĢĮéĿŀ
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    ä¸įéĶĻ
    -0.08
    og
    -0.08
    é½IJ
    -0.08
    ä¸įéĶĻçļĦ
    -0.08
    ace
    -0.07
    ä¸įå¾Ĺä¸į
    -0.07
    POSITIVE LOGITS
    éĤ£æł·
    0.14
    nor
    0.12
    èĢĮæĺ¯
    0.11
    éĤ£æł·çļĦ
    0.10
     nor
    0.10
    éĤ£åıª
    0.10
    ousel
    0.09
    å®ŀåľ¨å¤ª
    0.09
    è¿Ļå¼ł
    0.09
    è§Ĩ为
    0.09
    Activations Density 0.052%

    No Known Activations