© 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. 39700
    Prev
    Next
    INDEX
    Explanations

    negative, loss, savings, defects

    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
    _unc
    -0.08
    adesh
    -0.07
    æ³ī
    -0.07
     déroul
    -0.07
    leys
    -0.07
    ANC
    -0.07
    ä¸įç¡®å®ļ
    -0.07
    æ¡ĤåĨł
    -0.07
    èĢĮå¤į
    -0.07
     uncertainties
    -0.07
    POSITIVE LOGITS
    é¢Ŀå¤ĸçļĦ
    0.08
    çĶ¢çĶŁ
    0.07
    çıij
    0.07
     ekstra
    0.07
     surplus
    0.07
    ãģĿãģĵãģ§
    0.07
    é¢Ŀå¤ĸ
    0.07
    .extra
    0.07
    éĶĻä½į
    0.07
    èIJ½å·®
    0.07
    Activations Density 0.066%

    No Known Activations