© 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. 51367
    Prev
    Next
    INDEX
    Explanations

    code variables like x, y, t

    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
     vX
    -0.09
    Ïĩε
    -0.08
    éry
    -0.08
    _streams
    -0.07
    ç¡®æľī
    -0.07
    yel
    -0.07
    æı´æľĿ
    -0.07
    æIJĶ
    -0.07
    åĴĮä¸ļåĬ¡
    -0.07
    =-=-=-=-=-=-=-=-
    -0.07
    POSITIVE LOGITS
    že
    0.07
    asion
    0.07
    ãĢĤ
    0.06
    æĿ°
    0.06
    zens
    0.06
    ais
    0.06
    etsk
    0.06
     [,
    0.06
    æĺ
    0.06
    à¹Ħà¸ĩ
    0.06
    Activations Density 0.094%

    No Known Activations