© 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. 61484
    Prev
    Next
    INDEX
    Explanations

    number repetitions

    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
    æµģåĬ¨æĢ§
    -0.07
    æµģåĬ¨
    -0.07
     flows
    -0.07
    ylum
    -0.07
    ['__
    -0.07
    audi
    -0.07
    è£ĺ
    -0.06
    æµģç»ı
    -0.06
    AGMA
    -0.06
    flag
    -0.06
    POSITIVE LOGITS
    çŃ¹
    0.08
    mites
    0.08
     dừa
    0.07
     repetitions
    0.07
    éĩįå¤į
    0.07
    æĺİãģij
    0.07
    åĪ°ä½ł
    0.07
    adah
    0.07
    yttä
    0.07
    concat
    0.07
    Activations Density 0.022%

    No Known Activations