© 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. 51066
    Prev
    Next
    INDEX
    Explanations

    group by

    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
    ea
    -0.08
     bì
    -0.07
    åıįåĢĴæĺ¯
    -0.07
    راØŃ
    -0.07
     Rudd
    -0.07
    _SYN
    -0.07
    ä¸Ģå¹ħ
    -0.07
     vr
    -0.07
     unsupported
    -0.06
    chan
    -0.06
    POSITIVE LOGITS
    ç¬Ķ墨
    0.07
    _exports
    0.07
    rnd
    0.07
    Ale
    0.07
    owering
    0.07
    ernos
    0.07
     dắt
    0.07
    olds
    0.07
    irem
    0.07
    ews
    0.07
    Activations Density 0.003%

    No Known Activations