© 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. 63423
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    odb
    -0.07
    ellone
    -0.07
     leo
    -0.07
     Reb
    -0.07
    roz
    -0.06
    è¿Ľå±ķæĥħåĨµ
    -0.06
    лев
    -0.06
    å¼Ĺåħ°
    -0.06
    åħįå¾ģ
    -0.06
    UEL
    -0.06
    POSITIVE LOGITS
    å°ı家
    0.09
    avat
    0.07
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    0.07
    éļĺ
    0.07
    ahi
    0.07
    VIP
    0.07
    amay
    0.07
    terie
    0.07
     Contributors
    0.07
    讨
    0.07
    Activations Density 0.001%

    No Known Activations