© 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. 49183
    Prev
    Next
    INDEX
    Explanations

    chronology / reference / standard

    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
    åĨįæİ¥
    -0.08
    _ident
    -0.07
    æīĢ欲è¨Ģ
    -0.07
     اÙĦÙħØŃ
    -0.07
     Hess
    -0.07
    صب
    -0.07
    åĴĮèĩªå·±
    -0.07
    Rech
    -0.07
    á»ħu
    -0.07
    çĽĸä¸ĸ
    -0.07
    POSITIVE LOGITS
    æłĩåĩĨçļĦ
    0.08
    standard
    0.08
     استاÙĨدارد
    0.07
     standar
    0.07
     standard
    0.07
    æ¨Ļæºĸ
    0.07
    _standard
    0.07
    Ĩµ
    0.07
    æłĩåĩĨ
    0.07
     adjusted
    0.07
    Activations Density 0.228%

    No Known Activations