© 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. 61964
    Prev
    Next
    INDEX
    Explanations

    lecture or lectures given

    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
    æ³Ħ
    -0.10
    èįł
    -0.10
    GIN
    -0.09
    è°´
    -0.09
    ä¸ªå·¥ä½ľ
    -0.09
    ä¹ĭæĥħ
    -0.09
    äºĴåĪ©
    -0.09
    åĪĩ
    -0.09
    cheid
    -0.09
    leasing
    -0.09
    POSITIVE LOGITS
    讲座
    0.18
     lecture
    0.17
     lectures
    0.17
    讲课
    0.14
    æ¼Ķ讲
    0.14
    ecture
    0.13
    lecture
    0.13
    讲
    0.12
    æİĪ课
    0.12
    讲解
    0.12
    Activations Density 0.049%

    No Known Activations