© 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. 32695
    Prev
    Next
    INDEX
    Explanations

    states or existence

    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
    é¦ĸåħĪè¦ģ
    -0.08
    _MODULE
    -0.08
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
     sekaligus
    -0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.07
    Ø°Ùĩ
    -0.07
     Quart
    -0.07
    羣æŃ£çļĦ
    -0.07
     Sala
    -0.07
    .rl
    -0.07
    POSITIVE LOGITS
     entspr
    0.07
    符åIJĪè¦ģæ±Ĥ
    0.07
    åĮ¹éħį
    0.07
    éļħ
    0.07
     implicit
    0.07
    anner
    0.07
    è¶ħéŁ³
    0.07
    isor
    0.07
    符
    0.06
    åij±åij±
    0.06
    Activations Density 0.007%

    No Known Activations