© 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. 23888
    Prev
    Next
    INDEX
    Explanations

    why

    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
     Bou
    -0.09
    afa
    -0.09
    колÑĮ
    -0.08
    è¡«
    -0.08
     balk
    -0.08
     Yazı
    -0.08
    åı¯çĶ¨
    -0.08
    ä½°
    -0.08
    åŁİå¸ĤçļĦ
    -0.08
    then
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.11
    å½ĵä»ĸ
    0.09
    åĨįå¤ļ
    0.09
    æł¼å¤ĸ
    0.09
    è¿Łè¿Ł
    0.09
    è°Ĩ
    0.08
    æ·±åĮĸæĶ¹éĿ©
    0.08
    éĤ£æł·çļĦ
    0.08
    çIJĨ解åĴĮ
    0.08
     pinch
    0.08
    Activations Density 0.096%

    No Known Activations