© 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. 34110
    Prev
    Next
    INDEX
    Explanations

    place names with a city name ending in 'ved' or 'ys'

    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
    å¹´åħ¨çIJĥ
    -0.08
    -0.07
    Ỽt
    -0.07
     ÐĴÑģемиÑĢ
    -0.07
    çŃīåĽ½éĻħ
    -0.07
    åıĸåĨ³
    -0.07
    ä¸ŃåĽ½åĮº
    -0.06
    åħ¨è·¯æ®µ
    -0.06
    ouse
    -0.06
    atif
    -0.06
    POSITIVE LOGITS
    æĺ¯åħ¨åĽ½
    0.08
    åľ¨åħ¨åĽ½
    0.07
    æ±ŁåįĹ
    0.07
    èijĨ
    0.07
    ва
    0.07
    说åIJ§
    0.07
     nationally
    0.07
    ongo
    0.07
    大ä¸Ń
    0.07
    æ¬Ħ
    0.07
    Activations Density 0.480%

    No Known Activations