© 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. 32447
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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
    窥
    -0.07
    ÑģÑģен
    -0.07
    /car
    -0.07
    èĩ¼
    -0.06
    anne
    -0.06
    ä½ľåĪĻ
    -0.06
    unden
    -0.06
    çļĦåŃIJ
    -0.06
    ער
    -0.06
    èĩ³å°Ĭ
    -0.06
    POSITIVE LOGITS
     BOTH
    0.09
    ä¸Ģ次åıĪä¸Ģ次
    0.08
    两次
    0.08
    两èĢħ
    0.08
     both
    0.08
     Both
    0.08
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.08
    лиÑĩно
    0.08
    iously
    0.07
    Both
    0.07
    Activations Density 0.110%

    No Known Activations