© 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. 46391
    Prev
    Next
    INDEX
    Explanations

    Monday morning, irritating, personal, simplify things

    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
    åŃ©
    -0.08
    oeff
    -0.08
    ashboard
    -0.07
    å·®ä¸į
    -0.07
     mue
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    alsa
    -0.07
    翼翼
    -0.07
     ãĥĺãĥ«
    -0.06
     (!((
    -0.06
    POSITIVE LOGITS
    çĥģ
    0.07
    ()->
    0.07
    uled
    0.07
    ×Ļ×ĵ
    0.07
     reviewers
    0.07
    SEO
    0.07
    ç©İ
    0.07
    UDI
    0.06
    潤
    0.06
    é·¹
    0.06
    Activations Density 0.019%

    No Known Activations