© 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. 11430
    Prev
    Next
    INDEX
    Explanations

    Denmark, `visiting`, `cycles`

    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
     screen
    -0.08
    å±ı
    -0.07
    æݢ头
    -0.07
     Mushroom
    -0.06
     Womens
    -0.06
    å±ıå¹ķ
    -0.06
     Screen
    -0.06
    æĭĦ
    -0.06
    ore
    -0.06
    夹å±Ĥ
    -0.06
    POSITIVE LOGITS
    !!:
    0.08
    ä¸Ģæ±½
    0.07
    dice
    0.07
    ä¸Ģåľ°
    0.07
    quip
    0.07
    æıº
    0.07
    对ä¼ģä¸ļ
    0.07
    æĺ¨å¤ľ
    0.07
    èĦ±ä¸ĭ
    0.07
    assen
    0.07
    Activations Density 0.005%

    No Known Activations