© 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. 1456
    Prev
    Next
    INDEX
    Explanations

    MethodName or identifier name

    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
    人影
    -0.07
    对åı£
    -0.07
    èĢĮçŁ¥
    -0.07
    revet
    -0.07
    íĻĺ
    -0.07
     melay
    -0.07
    uny
    -0.07
    Lng
    -0.07
    uerta
    -0.07
    æĶ¾åľ¨å¿ĥä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ãĤīãĤĵ
    0.07
    iae
    0.07
    iek
    0.06
    ruzzo
    0.06
    âĢİ
    0.06
    zana
    0.06
    YC
    0.06
    ãĥĩãĥ¼
    0.06
    ordo
    0.06
    MethodName
    0.06
    Activations Density 0.598%

    No Known Activations