© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    academic journals and publications

    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
    è¡Ķ
    -0.08
    ä¹ĭæķ°
    -0.07
    ikum
    -0.07
    å¹³åı°åĴĮ
    -0.07
    orsi
    -0.07
    orer
    -0.07
    æľīæķĪæľŁ
    -0.07
    oru
    -0.07
    _FACTOR
    -0.07
    [%
    -0.07
    POSITIVE LOGITS
    гон
    0.07
    vm
    0.07
    æ»ij
    0.07
    plom
    0.07
     Flynn
    0.06
    allocate
    0.06
    جاد
    0.06
    ģ
    0.06
    usc
    0.06
    æ¢
    0.06
    Activations Density 0.007%

    No Known Activations