© 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. 64985
    Prev
    Next
    INDEX
    Explanations

    JSON format

    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
    ah
    -0.08
     forfait
    -0.07
    ys
    -0.07
    çIJĨè®ºåŁºç¡Ģ
    -0.07
    chten
    -0.07
    ator
    -0.07
    stad
    -0.07
    è¿ĩ度
    -0.07
    å¾Ĺä¸įåĪ°
    -0.06
    ç¢į
    -0.06
    POSITIVE LOGITS
    оÑĩе
    0.08
    à¹īà¸Ńà¸ĩ
    0.08
    è§Ħå®ļçļĦ
    0.08
    shine
    0.07
    æĮĩå®ļåľ°çĤ¹
    0.07
    丹丹
    0.07
    åŃ¦ä¹łä¹łæĥ¯
    0.07
    escaping
    0.07
    omanip
    0.07
     specified
    0.07
    Activations Density 0.002%

    No Known Activations