© 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. 24494
    Prev
    Next
    INDEX
    Explanations

    code and programming structures

    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
    chern
    -0.08
    ippo
    -0.07
    ragments
    -0.07
    缸å½ĵ
    -0.07
    زÙĩ
    -0.07
    à¸Ļà¸Ńà¸ĩ
    -0.07
    ienda
    -0.07
    uding
    -0.07
    opa
    -0.06
    ippi
    -0.06
    POSITIVE LOGITS
    æŀķ
    0.07
    ecat
    0.07
    lator
    0.07
    رÙĬÙģ
    0.06
    Lazy
    0.06
     clearTimeout
    0.06
    æį
    0.06
    Õ¡Öģ
    0.06
    à¹Ģว
    0.06
    åĽłæѤèĢĮ
    0.06
    Activations Density 0.001%

    No Known Activations