© 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. 46883
    Prev
    Next
    INDEX
    Explanations

    pow operator `**`

    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
    oli
    -0.08
    æݨ
    -0.08
    æķħ人
    -0.08
    -push
    -0.08
    æīĵçł´äºĨ
    -0.08
    æĪIJæľ¬æݧåĪ¶
    -0.08
    åt
    -0.08
    å¸Ĥåľºåıijå±ķ
    -0.07
    æĽĻ
    -0.07
    æŀĹçĭ¬
    -0.07
    POSITIVE LOGITS
    ercul
    0.07
    ä¸Ģæĸ¹
    0.07
    ä½Ļ
    0.07
    è¾ĥå°ı
    0.07
     abs
    0.07
     smaller
    0.07
    è¾Ĺ转
    0.07
     residual
    0.06
    _sizes
    0.06
    åıĮæĸ¹çļĦ
    0.06
    Activations Density 0.006%

    No Known Activations