© 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. 3980
    Prev
    Next
    INDEX
    Explanations

    remember things

    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
    让人
    -0.09
    å·¨
    -0.09
    ernes
    -0.09
    ç»į
    -0.09
    è®ĵ人
    -0.08
    åĪ°äºĨ
    -0.08
    rug
    -0.08
    令人
    -0.08
    æľīæľĽ
    -0.08
    饷
    -0.08
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.11
    PD
    0.10
    æľīä¸Ģä½į
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    æ¯ı天éĥ½
    0.09
    ÄŁu
    0.09
    .propTypes
    0.09
    人家
    0.08
    åĴ½
    0.08
    .defineProperty
    0.08
    Activations Density 0.017%

    No Known Activations