© 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. 28111
    Prev
    Next
    INDEX
    Explanations

    care providers and professionals

    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
    /callback
    -0.06
    eza
    -0.06
    çĶŁäº§å·¥èīº
    -0.06
    Ñĩив
    -0.06
    ozilla
    -0.06
    Stamp
    -0.06
    ç§ijåѦåIJĪçIJĨ
    -0.06
     عÙĤب
    -0.06
    é¼İ
    -0.06
    ä¸ĵå®¶åĽ¢éĺŁ
    -0.06
    POSITIVE LOGITS
    æī§ä¸ļ
    0.10
    å®ŀä¹łçĶŁ
    0.08
    æĮģè¯ģ
    0.08
    è§ģä¹ł
    0.08
    æī§çħ§
    0.08
    éĿ¢å¯¹
    0.08
    åľ¨å¤ĦçIJĨ
    0.08
     frontline
    0.08
     licensed
    0.07
    èĦ±åı£
    0.07
    Activations Density 0.343%

    No Known Activations