© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30396
    Prev
    Next
    INDEX
    Explanations

    loophole or glitch

    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
    afi
    -0.09
    åľ¨å¤ĸéĿ¢
    -0.09
    ingle
    -0.08
    æ°´åĩĨ
    -0.08
    æĥ¨
    -0.08
     Sinai
    -0.08
    -horizontal
    -0.08
    hir
    -0.08
    tain
    -0.08
    _runtime
    -0.08
    POSITIVE LOGITS
    ues
    0.11
    engers
    0.10
     looph
    0.10
    åľ°å¸¦
    0.09
    UES
    0.09
    åŃĺåľ¨äºİ
    0.09
     اÙĦسÙĬ
    0.09
     гоÑģ
    0.09
    æĢ§å¼º
    0.09
    etag
    0.09
    Activations Density 0.006%

    No Known Activations