© 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. 52106
    Prev
    Next
    INDEX
    Explanations

    code-related variables

    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
    ajo
    -0.08
    éĩįè¦ģçļĦäºĭæĥħ
    -0.08
    লা
    -0.07
    imity
    -0.07
    ObjectId
    -0.07
    chent
    -0.07
    еÑģа
    -0.07
    uszcz
    -0.07
    ewed
    -0.07
    AccessType
    -0.07
    POSITIVE LOGITS
    èĵ¬
    0.07
    æľīçĿĢ
    0.07
    å©Ĩ
    0.07
    ath
    0.07
    大å®ī
    0.07
    êµī
    0.07
    åŃĺåľ¨çĿĢ
    0.07
     dikat
    0.07
    jeta
    0.06
    ä»Ģä¹Īåij¢
    0.06
    Activations Density 0.055%

    No Known Activations