© 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. 21510
    Prev
    Next
    INDEX
    Explanations

    elected to a position

    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
    çłº
    -0.09
    orman
    -0.09
    pll
    -0.09
    ç»Ļä½łä»¬
    -0.08
    ERE
    -0.08
    unic
    -0.08
    OND
    -0.08
     полÑĥ
    -0.08
    æĮĤ
    -0.08
    ä¸į解
    -0.08
    POSITIVE LOGITS
    æĬķ票
    0.12
    ç«Ļéķ¿
    0.09
    é£İæ³¢
    0.09
     vote
    0.09
    èĩªæĿ¥
    0.08
    ÐIJÐĿ
    0.08
    lein
    0.08
    pires
    0.08
     vot
    0.08
     ballot
    0.08
    Activations Density 0.052%

    No Known Activations