© 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. 6588
    Prev
    Next
    INDEX
    Explanations

    word derivation or meaning

    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
    宣称
    -0.09
    ponder
    -0.09
    æŀ¶åŃIJ
    -0.08
    ä¸įçĶ±
    -0.08
    話ãĤĴ
    -0.08
    atten
    -0.08
    ìłģìĿ´
    -0.08
     thiá»ĩt
    -0.08
    æIJĶ
    -0.08
    è§īæĤŁ
    -0.08
    POSITIVE LOGITS
    è¡į
    0.10
    æѧ
    0.10
    _deriv
    0.10
    å¦Ĥæŀľæĺ¯
    0.10
     stret
    0.10
    ä¸ĢåŃĹ
    0.10
    imos
    0.09
    ê·¼
    0.09
    è¡įçĶŁ
    0.09
    è¿Ļ个è¯į
    0.09
    Activations Density 0.158%

    No Known Activations