© 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. 27539
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    à¥į
    -0.07
    stad
    -0.06
    /tty
    -0.06
    èĥ
    -0.06
    Ư
    -0.06
    [:-
    -0.06
     sekali
    -0.06
     commend
    -0.06
     straightforward
    -0.06
    æķĪ
    -0.06
    POSITIVE LOGITS
    idr
    0.08
    ritel
    0.07
    æµ·æ¶Ľ
    0.07
    åŃ¦ä¹łæķĻèĤ²
    0.07
    ometr
    0.07
    è¿Ļä¸ĸä¸Ĭ
    0.07
    otá
    0.07
    ask
    0.07
    zez
    0.07
    ardy
    0.07
    Activations Density 0.013%

    No Known Activations