© 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. 19079
    Prev
    Next
    INDEX
    Explanations

    album adele

    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
    ä¹ĭ称
    -0.08
    ä¸ĢæĬĬ
    -0.08
    æł¸
    -0.08
    æıĨ
    -0.08
    aket
    -0.08
    èIJį
    -0.08
    çīĩ段
    -0.08
    isoft
    -0.08
    oz
    -0.08
     Blacks
    -0.08
    POSITIVE LOGITS
    è¦ģç´ł
    0.10
    agne
    0.09
    æłī
    0.09
    seys
    0.09
    ä¸įå¿ĺ
    0.08
    æľ¬ç§ijçĶŁ
    0.08
    æ»Ł
    0.08
    onne
    0.08
    çµIJæĿŁ
    0.08
    ä¸ĭ次
    0.08
    Activations Density 0.004%

    No Known Activations