© 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. 32806
    Prev
    Next
    INDEX
    Explanations

    condominium, executor, Linux box

    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
    Trace
    -0.07
    è¾ŀåİ»
    -0.06
    èĩªçĶ¨
    -0.06
    el
    -0.06
    æ¯
    -0.06
    WM
    -0.06
     Barth
    -0.06
    elm
    -0.06
    çĶµç«Ļ
    -0.06
    并ä¸į大
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.09
     theirs
    0.08
    åIJĮæł·
    0.08
     ÑĤоже
    0.08
    ä¿Ń
    0.08
    acas
    0.07
    çŃīåħ¶ä»ĸ
    0.07
     latter
    0.07
    RAND
    0.07
    ä»İåħ¶
    0.07
    Activations Density 0.264%

    No Known Activations