© 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. 29690
    Prev
    Next
    INDEX
    Explanations

    medical history and condition descriptions

    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
    arend
    -0.08
    æľªçŁ¥çļĦ
    -0.07
    quine
    -0.07
    urban
    -0.07
     vare
    -0.07
    /*/
    -0.07
    é»ĺé»ĺçļĦ
    -0.07
    icom
    -0.07
    就差
    -0.07
    Cab
    -0.06
    POSITIVE LOGITS
    éĩįåľ¨
    0.08
     purs
    0.08
    寸
    0.08
    辨
    0.07
    表çݰ为
    0.07
    é¢ij
    0.07
    unto
    0.07
    温
    0.07
    æĹ¥ä¸Ĭ
    0.06
    è´¨åľ°
    0.06
    Activations Density 0.001%

    No Known Activations