© 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. 18118
    Prev
    Next
    INDEX
    Explanations

    falling or being taken down

    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
    arus
    -0.10
    æĭĽ
    -0.09
     Swing
    -0.09
    æĿª
    -0.09
    尾巴
    -0.09
    swing
    -0.09
    夤
    -0.09
    ä¸¤å¼ł
    -0.09
    æ¸ħæ°´
    -0.09
    æĺİæľĹ
    -0.09
    POSITIVE LOGITS
    姿åĬ¿
    0.11
    æijĶåĢĴ
    0.10
    趴
    0.10
    åĭķä½ľ
    0.10
    姿æĢģ
    0.09
    åĬ¨ä½ľ
    0.09
    åĮIJ
    0.09
    åŀŃ
    0.09
    è·Į
    0.09
    à¸Ļà¸Ńà¸Ļ
    0.09
    Activations Density 0.024%

    No Known Activations