© 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. 61527
    Prev
    Next
    INDEX
    Explanations

    names followed by actions

    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
    kid
    -0.08
    èĢģ人家
    -0.08
     hint
    -0.08
    ç½Ĺ
    -0.08
    åIJĮè¡Į
    -0.07
    ç»ĻäºĪäºĨ
    -0.07
    èĢĮåıĪ
    -0.07
     hints
    -0.07
    é»ĺé»ĺ
    -0.07
    ä½ıäºĨ
    -0.07
    POSITIVE LOGITS
    æľ¬äºº
    0.10
    ä¸įä»ħè¦ģ
    0.10
    çļĦæĥħæĦŁ
    0.09
    åĴĮä»ĸçļĦ
    0.09
    åĦĩ
    0.09
    å¿ĥä¸Ń
    0.09
    ramework
    0.09
    upported
    0.09
    æĮĸ
    0.09
    å¿ĥä¸ŃçļĦ
    0.09
    Activations Density 0.056%

    No Known Activations