© 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. 48147
    Prev
    Next
    INDEX
    Explanations

    software development keywords

    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
    ió
    -0.06
    èĢĮå¼Ĥ
    -0.06
    ä¸ŃåĽ½å¤§éĻĨ
    -0.06
    icch
    -0.06
    она
    -0.06
    å¥Ĺ
    -0.06
    ео
    -0.06
    oura
    -0.05
     "
    -0.05
    ifr
    -0.05
    POSITIVE LOGITS
    ª½
    0.09
     ìĺ¤ëŀ«
    0.09
    ¿Į
    0.09
    ®¤
    0.09
    actionDate
    0.09
    xeda
    0.09
    ç©Į
    0.09
    åħ¨éĥ¨æ¥¼å±Ĥ
    0.08
     onDataChange
    0.08
    æ¬łç¨İåħ¬åijĬ
    0.08
    Activations Density 0.404%

    No Known Activations