© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 35061
    Prev
    Next
    INDEX
    Explanations

    expecting a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ç³Ł
    -0.08
    å®ŀè´¨ä¸Ĭ
    -0.06
    éĽı
    -0.06
    ehl
    -0.06
    碰
    -0.06
    ugu
    -0.06
    说åIJ§
    -0.06
     itulah
    -0.06
    æĪij认为
    -0.06
     IDM
    -0.06
    POSITIVE LOGITS
    è¿ĺæľīåħ¶ä»ĸ
    0.09
    è¿ĺæľī个
    0.09
    è¿ĺæľīçĤ¹
    0.08
    è¿ĺåı¯èĥ½
    0.08
    è¿ĺæľīä¸Ģ个
    0.08
    è¿ĺ对
    0.08
    æľīæŶä¼ļ
    0.08
    noc
    0.08
    è¿ĺæĬĬ
    0.08
    è¿ĺåºĶå½ĵ
    0.08
    Activations Density 0.011%

    No Known Activations