© 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. 22073
    Prev
    Next
    INDEX
    Explanations

    Mustafa

    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
    ÑĥмÑĭ
    -0.08
     Dres
    -0.08
    ugu
    -0.07
    à¥Ĥल
    -0.07
    ÙĥÙī
    -0.07
    andia
    -0.07
    éĺħ读åİŁæĸĩ
    -0.07
    è¹
    -0.07
    idis
    -0.07
    渲
    -0.07
    POSITIVE LOGITS
    ixa
    0.08
    tern
    0.07
    éĿĴæĿ¾
    0.07
    yst
    0.07
    ix
    0.06
    عت
    0.06
    ind
    0.06
    åľ°ä¸Ĭ
    0.06
    æį·
    0.06
    Ö·
    0.06
    Activations Density 0.017%

    No Known Activations