© 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. 47838
    Prev
    Next
    INDEX
    Explanations

    knowledge and facts

    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
    æŁ¥çľĭæĽ´å¤ļ
    -0.11
    _tolerance
    -0.09
    æķ´æ²»
    -0.09
    esty
    -0.09
    æĹıèĩªæ²»
    -0.09
    iolet
    -0.08
    è¡·
    -0.08
    éĩįå¡ij
    -0.08
    .drawRect
    -0.08
    å¹Ħ
    -0.08
    POSITIVE LOGITS
    æľĢå¿«çļĦ
    0.11
    åIJį人
    0.10
    çŁ¥éģĵ
    0.10
    åľ¨åĵª
    0.10
     basic
    0.10
    毫ä¸į
    0.09
    äºĶ大
    0.09
    åĽĽå¤§
    0.09
    ä¹ŁçŁ¥éģĵ
    0.09
    è¾ĥå¿«
    0.09
    Activations Density 0.054%

    No Known Activations