© 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. 29630
    Prev
    Next
    INDEX
    Explanations

    regarding improvement to

    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
    ãĤ¤ãĤº
    -0.08
    imia
    -0.08
    kart
    -0.08
    tria
    -0.08
    stras
    -0.08
    thetic
    -0.08
    èĩªå¼º
    -0.08
    thon
    -0.07
    ÙĬاء
    -0.07
    究åħ¶åİŁåĽł
    -0.07
    POSITIVE LOGITS
     ìĤ¬íķŃ
    0.10
     ìĤ¬íķŃìĿĢ
    0.09
    ìĤ¬íķŃ
    0.09
     ìĤ¬íķŃìĿĦ
    0.08
    æѤäºĭ
    0.08
    äºĭéłħ
    0.08
    į
    0.08
    ance
    0.08
    ht
    0.07
    ri
    0.07
    Activations Density 0.111%

    No Known Activations