© 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. 42642
    Prev
    Next
    INDEX
    Explanations

    key-value separators

    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
    /--
    -0.07
    许å¤ļçļĦ
    -0.07
    æĪijå°±è¦ģ
    -0.07
    ãĤĤãģ®ãģ§ãģĤãĤĭ
    -0.06
    åĪ°äºĨä¸Ģ个
    -0.06
    /../
    -0.06
     '..',
    -0.06
    uds
    -0.06
    /<
    -0.06
     Felic
    -0.06
    POSITIVE LOGITS
    istory
    0.09
    åıĬéħį件
    0.08
    ierno
    0.08
    anzi
    0.08
    åıĬ设å¤ĩ
    0.08
    -wise
    0.08
    CString
    0.08
     모ë¦Ħ
    0.07
    åĴĮéĶĢåĶ®
    0.07
    mane
    0.07
    Activations Density 0.006%

    No Known Activations