© 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. 8289
    Prev
    Next
    INDEX
    Explanations

    download and language

    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
    ÙħÙĨت
    -0.07
    礴
    -0.07
    CBC
    -0.07
    æºIJæºIJ
    -0.07
    æĵį
    -0.07
    ÑĢÑĥ
    -0.07
    å°ĶèĴĻ
    -0.07
    alani
    -0.07
    ä¹Į鸦
    -0.07
     Certif
    -0.06
    POSITIVE LOGITS
    æ´¾éģ£
    0.07
    å¿Ĺæĺİ
    0.07
    碴
    0.07
    localhost
    0.06
    æĽĻ
    0.06
    彬
    0.06
    ëıĦì²´
    0.06
     calibrated
    0.06
    åĿıå¤Ħ
    0.06
    .Sdk
    0.06
    Activations Density 0.372%

    No Known Activations