© 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. 12323
    Prev
    Next
    INDEX
    Explanations

    human and specific contexts

    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
    æ¨
    -0.07
    èIJ½èIJ½
    -0.07
    裸
    -0.07
     videor
    -0.07
    å¾Ħ
    -0.07
    åķĨæľº
    -0.07
    zust
    -0.07
    =re
    -0.07
    群çļĦ
    -0.06
    ikian
    -0.06
    POSITIVE LOGITS
     Fert
    0.08
    è¿ĺ好
    0.08
    ä¹łæĥ¯äºİ
    0.07
     Terl
    0.07
    åģļä¸įåĪ°
    0.07
    otka
    0.07
    jem
    0.07
    åĴĮä¸ŃåĽ½
    0.07
     maupun
    0.06
    awe
    0.06
    Activations Density 0.177%

    No Known Activations