© 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. 34081
    Prev
    Next
    INDEX
    Explanations

    months or years

    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
    lescope
    -0.07
    好好
    -0.07
    å½±ä¸ļ
    -0.07
    ä½łåĪ«
    -0.07
    ä¸įçĿĢ
    -0.07
     Sar
    -0.07
    akas
    -0.07
    mern
    -0.07
    bern
    -0.07
    nö
    -0.07
    POSITIVE LOGITS
    à§įà¦ķ
    0.07
    IMPORTANT
    0.07
    Ø°ÙĬÙĨ
    0.07
    anser
    0.06
    airs
    0.06
    ALLEL
    0.06
    æĪªæŃ¢æĹ¥æľŁ
    0.06
    aho
    0.06
    кÑĤо
    0.06
    横
    0.06
    Activations Density 0.024%

    No Known Activations