© 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. 57466
    Prev
    Next
    INDEX
    Explanations

    when X press Ctrl

    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
     %.
    -0.08
     appunto
    -0.08
    asca
    -0.08
     //.
    -0.08
     wÅĤaÅĽnie
    -0.07
     "".
    -0.07
     thereof
    -0.07
    brids
    -0.07
    :.
    -0.07
    +.
    -0.07
    POSITIVE LOGITS
     обаÑĩе
    0.08
     tehát
    0.07
    ãģĵãģ¨ãĤĦ
    0.07
    åĽ½å®¶åĴĮåľ°åĮºçļĦ
    0.07
    æĹłè®ºæĺ¯
    0.07
    iep
    0.07
     λοι
    0.07
    社ä¼ļå®ŀ践活åĬ¨
    0.07
    çłĶ究表æĺİ
    0.07
    ç§ijæĬĢèĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.633%

    No Known Activations