© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    side-by-side or bottom corner

    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
    gian
    -0.08
    lega
    -0.08
    trinsic
    -0.08
    ienio
    -0.07
    gmt
    -0.07
    çĴĢ
    -0.07
    ython
    -0.07
    zinho
    -0.07
    icing
    -0.07
    çIJĨä¼ļ
    -0.07
    POSITIVE LOGITS
    éĥ½ä¸įåı¯èĥ½
    0.07
    ae
    0.07
     invece
    0.07
    æĢİä¹ĪåĬŀåij¢
    0.06
    æݧèĤ¡
    0.06
     Mes
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    åı¦ä¸Ģç§į
    0.06
     transit
    0.06
    ÙĦاÙĤ
    0.06
    Activations Density 0.013%

    No Known Activations