© 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. 51072
    Prev
    Next
    INDEX
    Explanations

    time duration units

    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
    utherland
    -0.09
    åĴĮç»Ħç»ĩ
    -0.08
    uner
    -0.08
    å¹´èıľ
    -0.08
    reno
    -0.07
    tron
    -0.07
     numberWith
    -0.07
    ykl
    -0.07
    atil
    -0.07
     Wochenende
    -0.07
    POSITIVE LOGITS
    ä½Ļ
    0.07
    pace
    0.06
    is
    0.06
     remainder
    0.06
    OrCreate
    0.06
     consign
    0.06
    ç²¾ç»ĨåĮĸ
    0.06
    itur
    0.06
    ç²¾èĩ´
    0.06
    paces
    0.06
    Activations Density 0.027%

    No Known Activations