© 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. 27417
    Prev
    Next
    INDEX
    Explanations

    legal states

    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
     unwanted
    -0.07
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    -0.07
    å°ıé¢ĺ
    -0.07
    åħ§çļĦ
    -0.07
    stones
    -0.06
    åĨħçļĦ
    -0.06
    usions
    -0.06
    游åĽŃ
    -0.06
    åį«çĶŁåĴĮ
    -0.06
     campan
    -0.06
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.11
    æīĢåľ¨
    0.11
    æīĢåľ¨çļĦä½įç½®
    0.11
     areas
    0.10
    çļĦéĥ¨ä½į
    0.09
    ãĤĭãģ¨ãģĵãĤį
    0.09
    æīĢåľ¨ä½įç½®
    0.09
     regions
    0.09
    åĮºåŁŁ
    0.08
    æīĢåľ¨åľ°åĮº
    0.08
    Activations Density 0.264%

    No Known Activations