© 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. 60982
    Prev
    Next
    INDEX
    Explanations

    founding, finish, victory, complexity

    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
    çīĪçļĦ
    -0.09
    çļĦæĪij
    -0.08
    æķĻäºİ
    -0.08
    æĤ¨å½ĵåīįçļĦä½įç½®
    -0.08
    åħ¶åIJİ
    -0.08
     whose
    -0.08
    å½¢ãģ§
    -0.08
    åıĮæĸ¹çļĦ
    -0.08
    åŀĭãģ®
    -0.07
    /Getty
    -0.07
    POSITIVE LOGITS
     selves
    0.09
    ability
    0.08
    以åıĬä¸İ
    0.08
    以åıĬåľ¨
    0.08
     ability
    0.08
    åĴĮæĪijçļĦ
    0.07
    asa
    0.07
    iphery
    0.07
     :]
    0.07
    åıĬ对
    0.07
    Activations Density 1.380%

    No Known Activations