© 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. 47824
    Prev
    Next
    INDEX
    Explanations

    years, numbers, or publication information

    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¨Ģ
    -0.08
    _Util
    -0.07
     defini
    -0.07
    åıªæľīèĩªå·±
    -0.07
    æł©æł©
    -0.07
    ±
    -0.07
    å¿ĥéħ¸
    -0.07
     оказÑĭваеÑĤÑģÑı
    -0.07
    åĽŀ头
    -0.07
    ếu
    -0.06
    POSITIVE LOGITS
    å¹´çļĦæŶéĹ´
    0.07
    akan
    0.07
    âĨĴ
    0.06
    éĻĦè¿ijçļĦ
    0.06
    aute
    0.06
    ést
    0.06
    ака
    0.06
    olves
    0.06
    afs
    0.06
    ë³Ģ
    0.06
    Activations Density 0.008%

    No Known Activations