© 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. 17255
    Prev
    Next
    INDEX
    Explanations

    legal 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
    tock
    -0.08
    åĴĮ第äºĮ
    -0.08
    werbung
    -0.08
    çİīå±±
    -0.07
    daq
    -0.07
    arf
    -0.07
    èĬľ
    -0.07
    adak
    -0.07
    orrow
    -0.07
    èŁĢ
    -0.07
    POSITIVE LOGITS
    /legal
    0.11
    åĴĮæ³ķå¾ĭ
    0.10
    fully
    0.10
    elijke
    0.10
    fulness
    0.10
    /pol
    0.09
    yer
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.08
    -pol
    0.08
    elijk
    0.08
    Activations Density 0.085%

    No Known Activations