© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32974
    Prev
    Next
    INDEX
    Explanations

    conditions / scrolling / state

    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
    ÙĤا
    -0.09
    å¿ĥæĤ¦
    -0.08
    身ä¸Ĭä¸ĭ
    -0.07
    EDIA
    -0.07
    ä¹ŁæĪIJäºĨ
    -0.07
    ημα
    -0.07
    ufer
    -0.07
    ÑħваÑĤÑĭ
    -0.07
    Ñĥдо
    -0.07
    äºİäºĭ
    -0.07
    POSITIVE LOGITS
    å·¥åĨµ
    0.06
    ongan
    0.06
     circonstances
    0.06
    è¦ģæ±Ĥ被åijĬ
    0.06
     wherein
    0.06
    ota
    0.06
     isLoggedIn
    0.06
     ambient
    0.06
     ÙĪÙĤبÙĦ
    0.06
    wan
    0.06
    Activations Density 0.250%

    No Known Activations