© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    output and response data

    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
    unting
    -0.07
    å¥Ĺ
    -0.07
    åºı
    -0.07
    ÑģÑıÑĤ
    -0.07
    åı¯ä¾Ŀ
    -0.07
    ç»į
    -0.07
    abi
    -0.07
    ungk
    -0.07
    isses
    -0.07
    ersist
    -0.07
    POSITIVE LOGITS
    èĤ¢
    0.07
    èµ°åIJijäºĨ
    0.07
    otte
    0.06
     oto
    0.06
    åĴ«å°º
    0.06
    éĥ½å¾Ī好
    0.06
    æıIJåĩºçļĦéĹ®é¢ĺ
    0.06
    keh
    0.06
    زÙĩ
    0.06
    amai
    0.06
    Activations Density 0.001%

    No Known Activations