© 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. 13275
    Prev
    Next
    INDEX
    Explanations

    html meta tags

    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
    ÙĨدÙĩ
    -0.08
    -str
    -0.08
    اÙĦØ©
    -0.08
     عاج
    -0.07
    EMAT
    -0.07
    chand
    -0.07
    åIJijæĹ¥
    -0.07
    stroy
    -0.07
    thood
    -0.07
     istr
    -0.07
    POSITIVE LOGITS
    ung
    0.07
     Quay
    0.06
    :description
    0.06
    থা
    0.06
     Hutchinson
    0.06
     Tew
    0.06
     optimum
    0.06
    åĮ¡
    0.06
    ebbe
    0.06
    éĺ³åİ¿
    0.06
    Activations Density 0.070%

    No Known Activations