© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50918
    Prev
    Next
    INDEX
    Explanations

    measures of size or quantity

    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
    åĭ¤
    -0.10
    裾
    -0.09
    gratis
    -0.09
    osal
    -0.09
    åĬ²
    -0.09
    è¹Ģ
    -0.09
     genu
    -0.09
    æĿĥçĽĬ
    -0.08
    éĥĬåĮº
    -0.08
    uy
    -0.08
    POSITIVE LOGITS
    -size
    0.11
    -sized
    0.10
    å·®ä¸įå¤ļ
    0.10
    å°±è·Ł
    0.09
    å¾Īå°ı
    0.09
    æĥħæĬ¥
    0.09
     sized
    0.09
    ç»ıéªĮåĴĮ
    0.09
    马åħĭ
    0.09
    åľ¨å½ĵåľ°
    0.09
    Activations Density 0.032%

    No Known Activations