© 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. 42511
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    å½ĵå¹´
    -0.08
    å½ĵå¹´çļĦ
    -0.07
     genu
    -0.07
    鸡精
    -0.07
    harma
    -0.07
     +
    -0.07
    .operations
    -0.06
    folger
    -0.06
    /
    -0.06
    ä¸ŃéĿĴå¹´
    -0.06
    POSITIVE LOGITS
    æĺİçļĦ
    0.09
    ANTE
    0.08
    .mag
    0.08
    ante
    0.08
    èIJ¦
    0.07
    ãģĭãģij
    0.07
    illon
    0.07
    apy
    0.07
    uble
    0.07
    .il
    0.07
    Activations Density 0.090%

    No Known Activations