© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    API attribute declarations

    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
    edBy
    -0.09
    ameni
    -0.08
    EXIST
    -0.08
    ç¾Į
    -0.08
    ếng
    -0.07
    大ä¸Ńåŀĭ
    -0.07
    upil
    -0.07
    Ïĥκε
    -0.07
    egah
    -0.07
    efs
    -0.07
    POSITIVE LOGITS
    确认
    0.07
    æ£ĢéªĮ
    0.07
     confirmation
    0.07
    æĭ¼
    0.06
     Heller
    0.06
     G
    0.06
    åľ¨ä½¿çĶ¨
    0.06
     grit
    0.06
    æµĭ
    0.06
    欢è¿İ
    0.06
    Activations Density 0.729%

    No Known Activations