© 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. 51679
    Prev
    Next
    INDEX
    Explanations

    prison or intestine context

    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
    计åĪĴåĴĮ
    -0.07
    arra
    -0.07
    çļĦè¿Ļä¸Ģ
    -0.07
    é«ĺç§ij
    -0.07
    peek
    -0.07
    /star
    -0.07
    ẹt
    -0.07
    å¾·ç½Ĺ
    -0.07
    人åħ³æ³¨
    -0.07
    åIJĦé¡¹çĽ®
    -0.07
    POSITIVE LOGITS
    orp
    0.07
    寡
    0.07
     meanwhile
    0.07
    çĶļ
    0.06
    åį³åı¯
    0.06
    åĻª
    0.06
    _driver
    0.06
    orable
    0.06
    ب
    0.06
    åį³åı¯å®ĮæĪIJ
    0.06
    Activations Density 0.226%

    No Known Activations