© 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. 55631
    Prev
    Next
    INDEX
    Explanations

    days of the week, especially Friday

    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
    é«¡
    -0.09
    ä½ĵä¼ļ
    -0.09
    ç§ĥ
    -0.08
    åĴĮå°ļ
    -0.08
    bay
    -0.08
    æĽ©
    -0.08
    5
    -0.08
    6
    -0.08
    9
    -0.08
    éĥĹ
    -0.08
    POSITIVE LOGITS
    çıĤ
    0.10
    ç§ĭåĨ¬
    0.09
    åĿĩæľī
    0.09
    åĿĩåı¯
    0.09
    ç°ª
    0.09
    åĿĩ为
    0.09
    ecast
    0.09
    ials
    0.08
    _except
    0.08
    éĥ½åľ¨
    0.08
    Activations Density 0.015%

    No Known Activations