© 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. 17848
    Prev
    Next
    INDEX
    Explanations

    likely values expressed as percentages

    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
    uil
    -0.08
    è´±
    -0.08
    交æĺĵä¼ļ
    -0.07
    ס×Ķ
    -0.07
    RITE
    -0.07
    ÏĦÏģο
    -0.07
    utr
    -0.07
    è¿Ļé¢Ĺ
    -0.07
    iny
    -0.07
    ?=
    -0.07
    POSITIVE LOGITS
    ersed
    0.07
    çļĦä¸Ģæĸ¹
    0.06
    воз
    0.06
     shall
    0.06
    çļĦä¸Ģ
    0.06
    åĴĮè§Ĩé¢ij
    0.06
     Tipp
    0.06
    æĹı
    0.06
    æ¡Ĥ
    0.06
    ére
    0.06
    Activations Density 0.020%

    No Known Activations