© 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. 60145
    Prev
    Next
    INDEX
    Explanations

    places and landmarks

    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
    AKE
    -0.08
    æīĭæı¡
    -0.07
    abant
    -0.07
    عÙĪ
    -0.07
    å½Ĵæł¹
    -0.07
     Devils
    -0.07
    ãģĿãģĨãģ§ãģĻãģŃ
    -0.07
    æł¼å¼ıçļĦ
    -0.07
    innen
    -0.07
    çļĦè¯Ŀ
    -0.07
    POSITIVE LOGITS
     Ùħباشرة
    0.10
     ÙĪÙĤبÙĦ
    0.10
     herum
    0.08
    ulla
    0.08
     hinweg
    0.07
     ÙĪبÙĬÙĨ
    0.07
    ł
    0.07
    åijĪ
    0.07
    æijĨæĶ¾
    0.07
    arel
    0.07
    Activations Density 0.230%

    No Known Activations