© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    email addresses or file extensions

    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
    halt
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    è°ĥæķ´å¥½
    -0.07
    rey
    -0.07
     Aller
    -0.07
     prê
    -0.07
    плÑİ
    -0.06
    èĬĤçļĦ
    -0.06
     Grosso
    -0.06
    æĻ°
    -0.06
    POSITIVE LOGITS
    å°Ķæĸ¯
    0.07
    èijĽ
    0.07
    ucu
    0.07
    é¢ĺ
    0.07
    achu
    0.07
    åĭī
    0.07
    ars
    0.06
    ours
    0.06
    วั
    0.06
     Idle
    0.06
    Activations Density 0.074%

    No Known Activations