© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    always or continuously

    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
    è¿Łè¿Ł
    -0.13
    ieg
    -0.11
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.09
    亲èĩª
    -0.09
    æĤłä¹ħ
    -0.09
    éķ¿æŶéĹ´
    -0.09
    é³ŀ
    -0.09
    å¤ļ项
    -0.09
    ä¸Ģ度
    -0.09
    åģĩåĨĴ
    -0.08
    POSITIVE LOGITS
    _Version
    0.10
    çªį
    0.10
    esti
    0.09
    æĸ°åįİ
    0.09
    è¯ĥ
    0.09
    æĻģ
    0.09
    ä¸Ģæł¹
    0.09
     Äijá»ĩ
    0.08
    åĩĨå¤ĩå·¥ä½ľ
    0.08
    饿
    0.08
    Activations Density 0.110%

    No Known Activations