© 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. 40729
    Prev
    Next
    INDEX
    Explanations

    curly braces and quotes

    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
    ĸ
    -0.07
    INCLUDED
    -0.07
    _ABORT
    -0.07
    ÄĻż
    -0.07
    polator
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    åĸĿåĴĸåķ¡
    -0.07
    ¥
    -0.07
    éric
    -0.07
    urut
    -0.07
    POSITIVE LOGITS
    snake
    0.08
    éģ¿åħįåĩºçİ°
    0.07
    afd
    0.07
    çī¹å°Ķ
    0.07
    ä¸Ģ级
    0.06
     VOID
    0.06
    coming
    0.06
    à§įব
    0.06
    两çĶ¨
    0.06
     Alten
    0.06
    Activations Density 0.001%

    No Known Activations