© 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. 31751
    Prev
    Next
    INDEX
    Explanations

    because of

    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
    åħ³äºİæĪij们
    -0.07
    对äºİéĤ£äºĽ
    -0.07
    Ø©
    -0.07
    _UNUSED
    -0.07
    ness
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    ense
    -0.06
    对äºİä¸Ģ个
    -0.06
    aven
    -0.06
    æĸĩæijĺ
    -0.06
    POSITIVE LOGITS
    ç§įç§įåİŁåĽł
    0.12
    åIJĦç§įåİŁåĽł
    0.12
    åħ¶åľ¨
    0.09
     ׼×ļ
    0.09
    以ä¸ĭæĸ¹å¼ı
    0.09
    æŃ¤èµ·
    0.08
     lack
    0.08
    å¾Ĺèµ·
    0.08
    à¹īม
    0.08
    “
    0.08
    Activations Density 0.004%

    No Known Activations