© 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. 32060
    Prev
    Next
    INDEX
    Explanations

    after all

    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
    adal
    -0.11
    esen
    -0.11
    æģ©
    -0.10
    åķ¼
    -0.09
    èĢģåĮĸ
    -0.09
    缼
    -0.09
    é¹Ń
    -0.08
     Rid
    -0.08
    åIJĮæł·çļĦ
    -0.08
    æ½Ĩ
    -0.08
    POSITIVE LOGITS
     indeed
    0.12
    çļĦç¡®
    0.11
    çļĦç¡®æĺ¯
    0.11
    ç«Łæĺ¯
    0.10
    æĺ¯å¤ļä¹Ī
    0.10
    æ¯ķç«Łæĺ¯
    0.10
    ç»Ī究
    0.10
    ç®ĹäºĨ
    0.10
    æŀľçĦ¶
    0.09
    æľªå¿ħ
    0.09
    Activations Density 0.070%

    No Known Activations