© 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. 24793
    Prev
    Next
    INDEX
    Explanations

    charged/un-charged states

    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
    æıIJåīį
    -0.07
    inari
    -0.07
    ä¸į误
    -0.07
    æıIJæĹ©
    -0.06
    cona
    -0.06
    æīĢæıIJä¾ĽçļĦ
    -0.06
    imore
    -0.06
    çŁ¥å·±
    -0.06
    oplan
    -0.06
     Reid
    -0.06
    POSITIVE LOGITS
    æļ«æĻĤ
    0.10
    æļ«
    0.10
    ä¸ŃéĹ´ä½ĵ
    0.10
     temporarily
    0.10
    æļĤ
    0.09
     tạm
    0.09
    以å¾ħ
    0.09
    .Then
    0.09
    æļĤæŶ
    0.09
     intermediate
    0.09
    Activations Density 0.116%

    No Known Activations