© 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. 7271
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and code"}, {"explanation": "mathematical operators and code elements"}, {"explanation": "operators and numeric sequences"}, {"explanation": "operators and code keywords"}, {"explanation": "programming operators and numeric values"}]

    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
    Not in Any Lists

    No Comments

    Negative Logits
     strtolower
    -0.06
     atop
    -0.06
    atch
    -0.06
    ={}
    -0.05
     Sing
    -0.05
    annel
    -0.05
    ä¸Ĭä¸į
    -0.05
    æĿIJæĸĻä¸İ
    -0.05
    ä¸Ĭ好
    -0.05
    ç§ī
    -0.05
    POSITIVE LOGITS
    _RED
    0.08
    attore
    0.08
    lds
    0.08
    yson
    0.08
    _INCREMENT
    0.08
    _Begin
    0.08
    ãĢįãĢģãĢĮ
    0.08
     yö
    0.08
    ãĢįãĢĮ
    0.08
    å¾ij
    0.08
    Activations Density 0.017%

    No Known Activations