© 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. 52132
    Prev
    Next
    INDEX
    Explanations

    value of composition

    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
    emaan
    -0.07
    =False
    -0.07
    çĢijå¸ĥ
    -0.07
    jas
    -0.07
    itori
    -0.07
    iales
    -0.07
    _reports
    -0.07
    itatea
    -0.07
    æĻĵ举
    -0.07
    =True
    -0.07
    POSITIVE LOGITS
    以åıĬåľ¨
    0.09
    (s
    0.09
    é¡¹çĽ®åıĬ
    0.08
    æĺ¯å¤ļå°ij
    0.07
    ambi
    0.07
    以åıĬå¦Ĥä½ķ
    0.07
    åıĬ管çIJĨ
    0.07
    èķī
    0.06
    说åĩº
    0.06
    æŃ»æ´»
    0.06
    Activations Density 0.060%

    No Known Activations