© 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. 16467
    Prev
    Next
    INDEX
    Explanations

    variable assignment or concatenation

    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
    å½¼æѤ
    -0.08
    ÑģÑĮ
    -0.08
    ordia
    -0.08
    ampus
    -0.07
    ogle
    -0.07
    emplo
    -0.07
    gte
    -0.07
    hangi
    -0.07
    æĺ¯éĩĩçĶ¨
    -0.07
     عÙĦÙĬÙĥÙħ
    -0.07
    POSITIVE LOGITS
    zien
    0.07
    ẩm
    0.07
    icar
    0.07
    aland
    0.07
    æº
    0.07
    å°±æĥ³
    0.07
    èıı
    0.07
    éĢļè¿ĩè¿ĻäºĽ
    0.07
    æĿ¥è¿ĩ
    0.06
    åİŁæĿ¥çļĦ
    0.06
    Activations Density 0.029%

    No Known Activations