© 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. 49508
    Prev
    Next
    INDEX
    Explanations

    teacher or student contexts

    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
    ensee
    -0.07
    lvl
    -0.07
    .son
    -0.07
    åIJ¬ä¸įæĩĤ
    -0.07
    айд
    -0.06
    pin
    -0.06
     Crescent
    -0.06
    æĥ³åİ»
    -0.06
    éŃĶ女
    -0.06
    æĬĵèIJ½å®ŀ
    -0.06
    POSITIVE LOGITS
    irt
    0.07
    é
    0.07
    Âł
    0.07
    Õ£
    0.07
    éra
    0.07
    amento
    0.07
    å¥Īä½ķ
    0.07
    ç§ijåѦçłĶ究éĻ¢
    0.07
    ele
    0.07
     [...]
    0.07
    Activations Density 2.145%

    No Known Activations