© 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. 12923
    Prev
    Next
    INDEX
    Explanations

    non-english characters or code fragments

    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
    äºĴ
    -0.07
     Technik
    -0.07
     Pen
    -0.06
    +'_
    -0.06
    äºĨä¸Ģå®ļçļĦ
    -0.06
    ä½ľèĢħåľ¨
    -0.06
    اÙĨÙĩ
    -0.06
    å½ĵåħ¶
    -0.06
    apture
    -0.06
    æº
    -0.06
    POSITIVE LOGITS
    à°Ĥà°¦
    0.08
    etul
    0.08
    SCALL
    0.07
    ëĮĢíijľ
    0.07
    å¾·å°Ķ
    0.07
    ungi
    0.07
    åľ¨å²Ĺ
    0.07
    à¸ŀà¹īà¸Ļ
    0.07
     viet
    0.06
    åį³å°Ĩ
    0.06
    Activations Density 0.001%

    No Known Activations