© 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. 33908
    Prev
    Next
    INDEX
    Explanations

    numbers and code strings

    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
    elte
    -0.07
    çķĮ
    -0.07
    ÑģÑĤÑı
    -0.06
    uns
    -0.06
    egel
    -0.06
     pong
    -0.06
    angers
    -0.06
    elt
    -0.06
    esel
    -0.06
    Ò
    -0.06
    POSITIVE LOGITS
    zyb
    0.07
    erah
    0.07
    FirstResponder
    0.07
     à¸ķà¸²à¸¡à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.07
    缸åħ³æ³ķå¾ĭ责任
    0.07
    秣åĶ®
    0.07
    InParameter
    0.07
    èĮ¹
    0.07
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.07
    EmptyEntries
    0.06
    Activations Density 0.011%

    No Known Activations