© 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. 57826
    Prev
    Next
    INDEX
    Explanations

    object declaration for classes and services

    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
    umba
    -0.07
     Yos
    -0.06
    reno
    -0.06
     Hig
    -0.06
    IgnoreCase
    -0.06
    /left
    -0.06
    æį®è¯´
    -0.06
    sq
    -0.06
    彦
    -0.06
    andy
    -0.06
    POSITIVE LOGITS
    onge
    0.08
    天山
    0.08
    å¸Ī大
    0.07
    gregate
    0.07
    วà¸ĩ
    0.07
    orgia
    0.07
    imai
    0.07
    uyên
    0.07
    _ELEM
    0.07
    åĴĮçĶŁäº§
    0.07
    Activations Density 0.075%

    No Known Activations