© 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. 21495
    Prev
    Next
    INDEX
    Explanations

    too late

    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
    TimeInterval
    -0.09
    enne
    -0.08
    ä¸įå®ļ
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    mma
    -0.08
    rück
    -0.08
     newly
    -0.08
    nette
    -0.08
    ä¸ĢæŶ
    -0.08
     newInstance
    -0.08
    POSITIVE LOGITS
    ernal
    0.11
    ä»İ严治
    0.10
    æĪijå·²ç»ı
    0.09
    oldt
    0.09
    bild
    0.09
    ãĥIJãĤ¹
    0.09
    æĥº
    0.09
    æŃ¢
    0.09
    ä¸Ģ声
    0.09
    ä¸ĢæŃ¥
    0.08
    Activations Density 0.005%

    No Known Activations