© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    real numbers

    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
    ovit
    -0.08
    formats
    -0.08
    chel
    -0.08
    åĴĮèµĦæºIJ
    -0.07
    ãģ£ãģĵ
    -0.07
    Îŀ
    -0.07
    cky
    -0.07
    niÄĩ
    -0.07
    á»Ĭ
    -0.07
    ifix
    -0.07
    POSITIVE LOGITS
    als
    0.08
    ernel
    0.07
    åħ¶è¡Į为
    0.07
    ÙħØŃ
    0.07
    丹
    0.06
     reales
    0.06
    ensed
    0.06
    REAL
    0.06
    ondes
    0.06
    axe
    0.06
    Activations Density 0.009%

    No Known Activations