© 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. 19151
    Prev
    Next
    INDEX
    Explanations

    AF_APPLETALK

    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
     tros
    -0.08
    Å¡a
    -0.07
    ì§ĵ
    -0.07
    opedia
    -0.07
    amarin
    -0.07
     تبع
    -0.07
    ÕŃ
    -0.07
    æŃ£å½ĵ
    -0.07
    лÑĬ
    -0.07
    anter
    -0.07
    POSITIVE LOGITS
    ner
    0.07
    ä¸Ģåı¶
    0.06
    çĽ¼
    0.06
    TextNode
    0.06
    ali
    0.06
    çİ
    0.06
    ä¸ĺ
    0.06
    ç§ijåѦæĢ§
    0.05
    phans
    0.05
     COPYING
    0.05
    Activations Density 0.012%

    No Known Activations