© 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. 20234
    Prev
    Next
    INDEX
    Explanations

    control flow and data operations

    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
    èvre
    -0.06
    blatt
    -0.06
    cha
    -0.06
    ↵
    -0.05
    夫
    -0.05
    Ø·
    -0.05
     Lib
    -0.05
    (
    -0.05
    èĪ¶
    -0.05
    夫çļĦ
    -0.05
    POSITIVE LOGITS
    åįİåĽ¾
    0.08
    åĴ¨è¯¢æĪij
    0.08
     CHARSET
    0.08
    _${
    0.08
    ä»¥ä¹łè¿ijå¹³
    0.08
    éĹ®åĮ»çĶŁ
    0.08
    馨
    0.08
    µľ
    0.08
     quizá
    0.08
    为ä¿ĥè¿Ľ
    0.07
    Activations Density 0.636%

    No Known Activations