© 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. 2055
    Prev
    Next
    INDEX
    Explanations

    resource and its related terms

    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
    zelf
    -0.10
    در
    -0.08
    tras
    -0.08
    áĥ£áĥłáĥĺ
    -0.08
    rens
    -0.07
    ówczas
    -0.07
    Å¡i
    -0.07
    ä¹ĭ交
    -0.07
    ourn
    -0.07
    czeÅĽ
    -0.07
    POSITIVE LOGITS
    ÙħÙĨد
    0.11
    æĢ§çĸ¾çĹħ
    0.09
    ç¦Ģ
    0.08
    fulness
    0.08
    åĴĮä¹īåĬ¡
    0.08
    ر
    0.08
    erias
    0.08
    åĮ®ä¹ı
    0.08
    inaldo
    0.08
    aat
    0.08
    Activations Density 0.024%

    No Known Activations