© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    list or numeric sequences

    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
    ister
    -0.07
     _|
    -0.06
     |_|
    -0.06
    ÙĪار
    -0.06
    anim
    -0.06
    èĽĻ
    -0.06
     Booker
    -0.06
    å¤į读
    -0.06
     Tw
    -0.06
    æŀģå¯Į
    -0.06
    POSITIVE LOGITS
    veau
    0.09
    ä¸įåŃĺåľ¨
    0.08
    aldi
    0.08
    é¤ĺ
    0.07
    èĥĮéĥ¨
    0.07
    åĸľæ¬¢
    0.07
     Riding
    0.07
    hoe
    0.07
    ryo
    0.07
    аÑģÑģив
    0.07
    Activations Density 0.001%

    No Known Activations