© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3040
    Prev
    Next
    INDEX
    Explanations

    musical instruments and players

    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
    edom
    -0.28
    èĪĨæĥħ
    -0.26
    ulen
    -0.23
    åħ¬åijĬ
    -0.23
    .gov
    -0.23
     fiscal
    -0.22
    objs
    -0.22
    æŁ¥éªĮ
    -0.22
    æķ°é¢Ŀ
    -0.22
    åĽ½åĨħå¤ĸ
    -0.22
    POSITIVE LOGITS
    ä¹IJåĻ¨
    0.58
    æ¼Ķå¥ı
    0.55
     guitar
    0.52
    åIJīä»ĸ
    0.47
    éĴ¢çIJ´
    0.42
    çIJ´
    0.42
    éŁ³ä¹IJ
    0.41
     instrument
    0.41
    æĬĢèīº
    0.41
    uitar
    0.40
    Activations Density 0.084%

    No Known Activations