© 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. 25354
    Prev
    Next
    INDEX
    Explanations

    opening files

    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
    íĮIJ
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
     hyper
    -0.07
     spont
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.06
    inek
    -0.06
    empo
    -0.06
    åŁ¹åħ»äºĨ
    -0.06
     Grove
    -0.06
     racked
    -0.06
    POSITIVE LOGITS
     оÑĤкÑĢÑĭваеÑĤÑģÑı
    0.09
     opened
    0.08
    /open
    0.08
     reopened
    0.08
     fopen
    0.08
    _CLOSED
    0.08
     abierto
    0.08
     openings
    0.08
     оÑĤкÑĢÑĭÑĤÑĮ
    0.08
    isOpen
    0.08
    Activations Density 0.050%

    No Known Activations