© 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. 34814
    Prev
    Next
    INDEX
    Explanations

    deeper into

    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
    -animate
    -0.08
     riktigt
    -0.07
    å¹´é¾Ħåľ¨
    -0.07
    Gatt
    -0.07
    âĢİ
    -0.07
    emergen
    -0.07
    æv
    -0.07
    йÑģ
    -0.07
    éĺ³åı°ä¸Ĭ
    -0.07
    åľ°åĿĢä½įäºİ
    -0.07
    POSITIVE LOGITS
     etc
    0.09
    äºĨä¸ĭ
    0.09
    ambil
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    ä¸Ģä¸ĭå°±
    0.07
    yson
    0.06
    ymology
    0.06
    chant
    0.06
     both
    0.06
     inca
    0.06
    Activations Density 0.001%

    No Known Activations