© 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. 51586
    Prev
    Next
    INDEX
    Explanations

    back pitch

    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
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.08
    اÙĨÙĬا
    -0.07
    ாமà¯į
    -0.07
    ands
    -0.07
    edelta
    -0.07
    alie
    -0.07
    ividade
    -0.07
    lichen
    -0.07
    ualmente
    -0.07
    encial
    -0.07
    POSITIVE LOGITS
    èĢĮèµ°
    0.07
    º
    0.07
    æĥļ
    0.07
     ê¹Ķ
    0.07
    éĤ
    0.07
    ritch
    0.07
    ebb
    0.07
    wit
    0.07
    PELL
    0.07
    erder
    0.07
    Activations Density 0.222%

    No Known Activations