© 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. 40951
    Prev
    Next
    INDEX
    Explanations

    legal and conditional terms

    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
     sprung
    -0.07
     Hoy
    -0.07
    æĸ¯åį¡
    -0.07
    Ban
    -0.07
    IES
    -0.07
    ÛĮدÛĮ
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    å½Ĵ
    -0.07
    ban
    -0.06
    Logging
    -0.06
    POSITIVE LOGITS
    çļĦåīįæıIJä¸ĭ
    0.10
     oczywiÅĽcie
    0.09
    åīįæıIJä¸ĭ
    0.08
    为åīįæıIJ
    0.08
    åı¯è¡ĮçļĦ
    0.07
    éĻIJ度
    0.07
     конеÑĩно
    0.07
    çļĦåīįæıIJ
    0.07
    azel
    0.07
    éĢĤ度çļĦ
    0.07
    Activations Density 0.065%

    No Known Activations