© 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. 31681
    Prev
    Next
    INDEX
    Explanations

    domain specific 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
    åĴĮçī¹çĤ¹
    -0.09
    unj
    -0.08
    اء
    -0.08
    åĴĮè¦ģæ±Ĥ
    -0.08
    ä¸ĭèį¯
    -0.08
    åĴĮç»ıéªĮ
    -0.08
    çļĦéĹ®é¢ĺæĺ¯
    -0.07
    ä¸ľè¥¿
    -0.07
    RowIndex
    -0.07
    åľ°åĮºåĴĮ
    -0.07
    POSITIVE LOGITS
    çIJĨ念
    0.08
    秩åºı
    0.08
    /rest
    0.08
    æĢĿè·¯
    0.07
    æ°ĽåĽ´
    0.07
     experience
    0.07
    è§Ĥ
    0.07
    anos
    0.07
     outlook
    0.07
    çī¹æľīçļĦ
    0.07
    Activations Density 0.083%

    No Known Activations