© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 786
    Prev
    Next
    INDEX
    Explanations

    plot points and book types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æĺ¯æ¯Ķè¾ĥ
    -0.34
    edor
    -0.34
    æĪĸèĢħæĺ¯
    -0.33
    åīįè¿°
    -0.31
    éĿŀ常é«ĺ
    -0.30
     mentioned
    -0.29
    ä¸Ĭè¿°
    -0.29
    éĤ£ä¸ªæŶåĢĻ
    -0.28
    æ¯Ķå¦Ĥ说
    -0.28
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.28
    POSITIVE LOGITS
    —and
    0.31
     bestselling
    0.30
     secrets
    0.28
    æĸ°åŀĭ
    0.27
     elusive
    0.27
    —a
    0.27
     forgotten
    0.27
     novels
    0.27
     dreams
    0.25
     ebook
    0.25
    Activations Density 0.136%

    No Known Activations