© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    اÙĭ
    -0.12
    Ùĭا
    -0.09
    æĢ§åľ°
    -0.09
    ous
    -0.08
    ties
    -0.08
    edException
    -0.08
    ese
    -0.08
    ings
    -0.07
    åĦ¿
    -0.07
    à¹ĥà¸Ī
    -0.07
    POSITIVE LOGITS
    ftware
    0.08
    .au
    0.08
    .gz
    0.08
    redicate
    0.07
    身临åħ¶å¢ĥ
    0.07
    转载èĩ³
    0.06
    hti
    0.06
    atique
    0.06
    AbsolutePath
    0.06
    ë§IJ
    0.06
    Activations Density 0.170%

    No Known Activations