© 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. 8328
    Prev
    Next
    INDEX
    Explanations

    pathways and identifiers

    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
    eldon
    -0.07
     Veel
    -0.07
    izr
    -0.07
    ç»ıæµİå®ŀåĬĽ
    -0.07
    _Local
    -0.07
    æħij
    -0.06
    çļĵ
    -0.06
     cú
    -0.06
    åīį款
    -0.06
     choc
    -0.06
    POSITIVE LOGITS
    atham
    0.08
    æ¯ķç«Ł
    0.07
    ents
    0.07
    berger
    0.07
     übrigens
    0.07
    éĢ¼
    0.07
    çķ¢ç«Ł
    0.07
    赶路
    0.07
    ÑģÑĤо
    0.06
    ãĥıãĤ¦ãĤ¹
    0.06
    Activations Density 0.006%

    No Known Activations