© 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. 42183
    Prev
    Next
    INDEX
    Explanations

    first or second part

    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
    mgr
    -0.07
    kel
    -0.07
    omy
    -0.07
    活水
    -0.07
    æIJŃä¸Ĭ
    -0.06
    istian
    -0.06
     huom
    -0.06
    ä½łæĺ¯æĪijçļĦ
    -0.06
    Ùħاج
    -0.06
    åĩīæ°´
    -0.06
    POSITIVE LOGITS
    iore
    0.08
    é¯ĸ
    0.08
    /original
    0.08
     Moraes
    0.08
     ones
    0.07
    ledes
    0.07
    ICLE
    0.07
    cimento
    0.07
    /main
    0.07
    psilon
    0.06
    Activations Density 0.041%

    No Known Activations