© 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. 32170
    Prev
    Next
    INDEX
    Explanations

    html tag ending

    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
    æŃ»äºº
    -0.08
    转载请注æĺİåĩºå¤Ħ
    -0.08
     mons
    -0.08
    ế
    -0.08
    kip
    -0.07
    _SCR
    -0.07
     Engenh
    -0.07
    engg
    -0.07
    elh
    -0.07
     Dead
    -0.07
    POSITIVE LOGITS
    麻麻
    0.06
    /facebook
    0.06
    uzzi
    0.06
    æľīè¿Ļæł·çļĦ
    0.06
    å¦ĤæѤ
    0.06
    åĽ¢åĽ¢
    0.06
    åºķä¸ĭ
    0.06
    循
    0.06
    å§Ĺ
    0.06
    eted
    0.06
    Activations Density 0.231%

    No Known Activations