© 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. 34132
    Prev
    Next
    INDEX
    Explanations

    abbreviations and symbols like Lambda, CERs, REG, deg

    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
    ÏĥÏĦε
    -0.07
    ately
    -0.07
    tpl
    -0.07
    èĩªçŁ¥
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
     ï¿¥
    -0.07
    è±
    -0.07
    Ĩµ
    -0.07
    hipster
    -0.07
    POSITIVE LOGITS
    æĬ¬é«ĺ
    0.07
    顾åIJįæĢĿä¹ī
    0.06
    åĬ¡
    0.06
    \_
    0.06
    éĥ¨éŨåĴĮ
    0.06
    ẻ
    0.06
    åİĨ
    0.06
    _{
    0.06
    ä¹ĭé¦ĸ
    0.06
     Forget
    0.06
    Activations Density 0.036%

    No Known Activations