© 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. 7346
    Prev
    Next
    INDEX
    Explanations

    special syntax placeholders and identifiers

    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
    åŃ¦æł¡åľ¨
    -0.08
    zó
    -0.07
    çĸ±
    -0.07
    asz
    -0.07
    âĸª
    -0.07
     اØŃ
    -0.07
    elts
    -0.07
    pha
    -0.07
    å®ĥ以
    -0.07
    неж
    -0.07
    POSITIVE LOGITS
    lyn
    0.07
    ÑĥÑĩ
    0.07
    ä¸įåĩº
    0.07
    纵
    0.07
     sponsor
    0.06
    å¤ĸ
    0.06
    ponsor
    0.06
    ä¹ĭä¸į
    0.06
    ida
    0.06
    ç²¾
    0.06
    Activations Density 0.101%

    No Known Activations