© 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. 49497
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    {}",
    -0.08
    اتÛĮ
    -0.08
    lfw
    -0.07
     schlieÃŁlich
    -0.07
    ————————————————
    -0.07
    -0.07
    chos
    -0.07
    otella
    -0.07
    yard
    -0.07
    ¶
    -0.07
    POSITIVE LOGITS
    fri
    0.07
    ier
    0.07
    el
    0.07
    ÛĮ
    0.06
    ãģªãģĦ
    0.06
     '&#
    0.06
    æ
    0.06
    ئÙĥ
    0.06
    åħ¬åı·
    0.06
    nya
    0.06
    Activations Density 0.186%

    No Known Activations