© 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. 41888
    Prev
    Next
    INDEX
    Explanations

    recursive include module import

    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
    INT
    -0.07
    çŃīçĿĢä½ł
    -0.06
    plete
    -0.06
    ä¸īåħ«
    -0.06
    ÙĪدÙĩ
    -0.06
     INT
    -0.06
    agam
    -0.06
    anny
    -0.06
    湿æ°Ķ
    -0.06
    纲
    -0.06
    POSITIVE LOGITS
     insomma
    0.07
    ights
    0.07
    eks
    0.07
    yms
    0.07
    ltk
    0.07
    OfClass
    0.07
     ÐijÑĥдÑĥ
    0.07
    /lg
    0.07
     strÄĥ
    0.07
    arda
    0.07
    Activations Density 0.164%

    No Known Activations