© 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. 39845
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    æŁIJäºĽ
    -0.11
    quate
    -0.09
    æĦŁ
    -0.09
    éģ£
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
    ocy
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    agus
    -0.08
    URLException
    -0.08
    utron
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.14
    æľīä¸įåIJĮçļĦ
    0.10
     different
    0.10
    çĭ¬çī¹
    0.10
    different
    0.10
    åĽĽç§į
    0.09
    çĭ¬çī¹çļĦ
    0.09
    ç±»åŀĭçļĦ
    0.09
    ä¸ļæĢģ
    0.09
    ä¸īç§į
    0.09
    Activations Density 0.071%

    No Known Activations