© 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. 37813
    Prev
    Next
    INDEX
    Explanations

    physical and mathematical formulas

    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
    æĽ´è¡£
    -0.07
    ÛĮتÛĮ
    -0.07
    趾
    -0.07
    彬
    -0.07
    lander
    -0.07
    roman
    -0.07
    oja
    -0.07
    imli
    -0.07
    Ñģив
    -0.07
    ÑĤей
    -0.07
    POSITIVE LOGITS
    çļĦä¼Łå¤§
    0.08
    _wr
    0.06
    æѦè£ħ
    0.06
     à¤Ĩव
    0.06
    exper
    0.06
    æ®ĩ
    0.06
    .nano
    0.06
    inds
    0.06
    Ñĭл
    0.06
     ripr
    0.06
    Activations Density 0.001%

    No Known Activations