© 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. 31812
    Prev
    Next
    INDEX
    Explanations

    poor quality or prognosis

    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
    лÑĮка
    -0.09
    evat
    -0.09
    áĥ£áĥłáĥĺ
    -0.09
    блÑİ
    -0.09
    åĴĮ帮åĬ©
    -0.09
    resso
    -0.09
    à§Ģয়
    -0.08
    好çļĦ产åĵģ
    -0.08
    ÑĪеÑģÑĤв
    -0.08
    taggio
    -0.08
    POSITIVE LOGITS
    ly
    0.10
    ened
    0.10
    ening
    0.09
     miser
    0.09
    ulent
    0.09
    (er
    0.08
    ä¸įåłª
    0.08
    -quality
    0.07
    (
    0.07
    åĬ£
    0.07
    Activations Density 0.039%

    No Known Activations