© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63968
    Prev
    Next
    INDEX
    Explanations

    exponents or powers

    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
    被åijĬçŁ¥
    -0.07
    n
    -0.06
    kow
    -0.06
    ç½Ħ
    -0.06
    éĻĮ
    -0.06
    çIJĥéĺŁ
    -0.06
    åĩĢåľŁ
    -0.06
    åħ³çħ§
    -0.06
    ä¹IJéĺŁ
    -0.06
    çļĦä»·åĢ¼
    -0.06
    POSITIVE LOGITS
    TypeInfo
    0.08
    Ú©Ø´
    0.08
    èIJ¤çģ«
    0.08
    å®ŀåĬĽåĴĮ
    0.08
    èĩªè¡ĮæıIJä¾Ľ
    0.08
    iminal
    0.07
    Ïģγ
    0.07
    adem
    0.07
    agr
    0.07
    ullen
    0.07
    Activations Density 0.003%

    No Known Activations