© 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. 47936
    Prev
    Next
    INDEX
    Explanations

    years

    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
    æĶ¾åѦ
    -0.10
    ny
    -0.10
    å¤Ħäºİ
    -0.09
    èµĽåIJİ
    -0.09
    éĿĴå¹´
    -0.09
    æĿ¥èĩªäºİ
    -0.09
    ä¹ĭ乡
    -0.08
    æŀŀ
    -0.08
    èĩªæĦ¿
    -0.08
    æĿ¥èĩª
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģå¹´
    0.18
    æĸ°çļĦä¸Ģå¹´
    0.14
    ä¸Ģå¹´
    0.12
    å±ķæľĽ
    0.12
    าว
    0.11
    åIJĮå¹´
    0.10
    ä¸ĬåįĬå¹´
    0.10
    åħ¨å¹´
    0.10
     year
    0.10
    imus
    0.10
    Activations Density 0.086%

    No Known Activations