© 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. 65315
    Prev
    Next
    INDEX
    Explanations

    boundary condition

    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
    ÙħاÙħ
    -0.08
    ç¨ĭ度ä¸Ĭ
    -0.08
    æ¦Ĥ念çļĦ
    -0.08
    ighted
    -0.08
    leccion
    -0.08
    olist
    -0.08
    âu
    -0.07
    panse
    -0.07
    -than
    -0.07
    lej
    -0.07
    POSITIVE LOGITS
     conditions
    0.08
    -data
    0.06
    è¯Ŀ说
    0.06
    à¸ģรà¸ĵà¹Į
    0.06
    ns
    0.06
     values
    0.06
     dict
    0.06
    stel
    0.06
    åĵ
    0.06
    ls
    0.06
    Activations Density 0.003%

    No Known Activations