© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    cosmology and discoveries

    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
    Handled
    -0.08
    odge
    -0.07
    æ´»åĬ¨åľ°çĤ¹
    -0.07
    åIJĮçIJĨ
    -0.07
    平顺
    -0.07
    为ä»ĸ人
    -0.07
    åħ¸åŀĭ
    -0.07
    çĨŁç»ĥæĵįä½ľ
    -0.07
    åĨľæĿijå±ħæ°ij
    -0.07
    åij¨ä¸Ģèĩ³åij¨äºĶ
    -0.07
    POSITIVE LOGITS
     discoveries
    0.09
    æİ¢æµĭ
    0.08
    çļĦéĩį大
    0.08
    åĽ½éĻħåIJĪä½ľ
    0.08
    çŃīéĩį大
    0.08
     thrilling
    0.08
     eagerly
    0.08
     cosm
    0.08
     exciting
    0.08
    æ¿ĢåĬ¨
    0.07
    Activations Density 0.034%

    No Known Activations