© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31087
    Prev
    Next
    INDEX
    Explanations

    .exit or exiting

    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
    lie
    -0.07
    宿
    -0.06
    ç´§
    -0.06
    åĽłåħ¬
    -0.06
    Ùĩب
    -0.06
    ç¦ħ
    -0.06
    æµ®çĶŁ
    -0.06
    TestClass
    -0.06
     Spiral
    -0.06
     Riz
    -0.06
    POSITIVE LOGITS
    åĩºåİ»çļĦ
    0.09
    éĢĢåĩº
    0.09
     efectiv
    0.08
     exits
    0.08
    ahoo
    0.08
     exiting
    0.08
    åĩºåİ»äºĨ
    0.07
    æĪIJåħ¨
    0.07
    .exit
    0.07
     removable
    0.07
    Activations Density 0.002%

    No Known Activations