© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10174
    Prev
    Next
    INDEX
    Explanations

    anticipation that

    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
    æĢ»éĥ¨
    -0.09
    身å¿ĥåģ¥åº·
    -0.08
    橱
    -0.08
    ãģĿãģĨãģ§
    -0.08
    æīĢåľ¨
    -0.08
    èĭ¥å¹²
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    vice
    -0.08
    ä¹ĭ乡
    -0.08
    POSITIVE LOGITS
    ãģ§ãģ®
    0.10
    uka
    0.09
     ÙĪعÙĦÙī
    0.09
    /if
    0.09
     vicinity
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.08
    /on
    0.08
    ABOUT
    0.08
    quared
    0.08
    è¿ĺä¸įæĺ¯
    0.08
    Activations Density 0.622%

    No Known Activations