© 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. 25562
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
    istr
    -0.09
    à¹ĥà¸Ī
    -0.08
    оÑĢод
    -0.08
    iglio
    -0.07
    aic
    -0.07
    tenham
    -0.07
    ting
    -0.07
    ularity
    -0.07
    à§į
    -0.07
    anagan
    -0.07
    POSITIVE LOGITS
    adies
    0.08
     túc
    0.07
    zaak
    0.07
    _MATH
    0.07
    碧波
    0.07
    æ°§åĮĸ碳
    0.07
    hia
    0.07
    efined
    0.07
     Má»Ļ
    0.06
    室ä¸Ģåİħ
    0.06
    Activations Density 0.045%

    No Known Activations