© 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. 26377
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code fragments

    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
    èĢĮéĿŀ
    -0.07
    ISS
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    _HIDDEN
    -0.07
    ä¸į计
    -0.07
    ä¸į太
    -0.07
    oru
    -0.07
    工信
    -0.06
    å·¥ä¸ļåĴĮä¿¡æģ¯åĮĸ
    -0.06
    indelijk
    -0.06
    POSITIVE LOGITS
     anymore
    0.16
    æľīä»»ä½ķ
    0.13
    ä»»ä½ķè´¹çĶ¨
    0.09
    akaan
    0.09
    ecessarily
    0.09
     anything
    0.09
    ä»»ä½ķ
    0.09
    ä»»ä½ķ人
    0.09
    åģļä»»ä½ķ
    0.09
     altogether
    0.09
    Activations Density 0.071%

    No Known Activations