© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62824
    Prev
    Next
    INDEX
    Explanations

    seeking help

    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
    æµĬ
    -0.08
    iaux
    -0.07
    次äºİ
    -0.07
    éķ¿è¾¾
    -0.07
    '][]
    -0.07
     clim
    -0.07
    å±ŀ
    -0.07
     Ðļл
    -0.07
    æĺ¼
    -0.07
    ouched
    -0.07
    POSITIVE LOGITS
    cef
    0.07
    irs
    0.07
    ickey
    0.07
    orius
    0.07
    è¿Ļç§įåģļæ³ķ
    0.07
    幸ç¦ıå¿«ä¹IJ
    0.07
    ä»Ģä¹Īåij¢
    0.07
    æĪijè§īå¾Ĺ
    0.07
    áºŃy
    0.07
    åıªè¦ģèĥ½
    0.07
    Activations Density 0.001%

    No Known Activations