© 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. 17667
    Prev
    Next
    INDEX
    Explanations

    specific nouns and technical terms

    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
    æĤłæĤł
    -0.08
    ongen
    -0.08
    æİĸ
    -0.08
    otti
    -0.07
    amp
    -0.07
    åįĴ
    -0.07
    æ¶ħ
    -0.07
    åħ¨ä½ĵå¸ĪçĶŁ
    -0.07
     Ùħد
    -0.07
    Ĥ¤
    -0.07
    POSITIVE LOGITS
     nond
    0.08
    apot
    0.07
    ice
    0.07
     بعدÙĩ
    0.07
    åĪĻåı¯ä»¥
    0.06
    turut
    0.06
    opot
    0.06
     Figu
    0.06
     kanal
    0.06
    èĪĮå°ĸ
    0.06
    Activations Density 0.290%

    No Known Activations