© 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. 60038
    Prev
    Next
    INDEX
    Explanations

    number literals and code keywords

    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
    éľĦ
    -0.06
    âĢ¦
    -0.06
    út
    -0.06
    оба
    -0.06
    fel
    -0.06
    姬
    -0.06
    dn
    -0.06
    缴
    -0.06
    æ¼Ĥ亮
    -0.06
    OLE
    -0.06
    POSITIVE LOGITS
    åĥıä½ł
    0.08
    çļĦä½ł
    0.08
    ington
    0.08
    带åİ»
    0.08
    ä½łè¿Ļä¹Ī
    0.08
    akis
    0.08
     restante
    0.08
    æķ£çĻ¼
    0.07
    ewire
    0.07
    å°±éĢģ
    0.07
    Activations Density 0.001%

    No Known Activations