© 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. 11734
    Prev
    Next
    INDEX
    Explanations

    as described

    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
    ahaya
    -0.07
    ugio
    -0.07
    ancia
    -0.07
    /bin
    -0.07
    Bin
    -0.07
    atering
    -0.06
    æħ¾
    -0.06
     Kudus
    -0.06
    ÑĨенÑĤÑĢ
    -0.06
    eria
    -0.06
    POSITIVE LOGITS
     described
    0.11
    çļĦæııè¿°
    0.09
     aforementioned
    0.08
    æīĢè¿°çļĦ
    0.08
    -pr
    0.08
    ä¸Ĭè¿°äºĭå®ŀ
    0.08
    ä¸Ĭè¿°
    0.08
    æııè¿°
    0.08
    entions
    0.08
    æııè¿°çļĦ
    0.08
    Activations Density 0.293%

    No Known Activations