© 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. 51127
    Prev
    Next
    INDEX
    Explanations

    list or map structure

    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
    azor
    -0.08
    åĪĩãĤĬ
    -0.06
    anity
    -0.06
    beck
    -0.06
    享
    -0.06
    å¨ĺ
    -0.06
     simply
    -0.06
    F
    -0.06
    åħ®
    -0.06
    åĩıè´Ł
    -0.06
    POSITIVE LOGITS
    è¿Ļå°ıåŃIJ
    0.08
    ếp
    0.08
    ÅĪa
    0.08
     полиÑĨ
    0.07
    人åĽŀå¤į
    0.07
    اشت
    0.07
    åIJĦéķĩ
    0.07
    æŃ¤èµ·
    0.07
    åIJİæĿ¥åıĪ
    0.07
    OURS
    0.07
    Activations Density 0.061%

    No Known Activations