© 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. 21373
    Prev
    Next
    INDEX
    Explanations

    table and code symbols

    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
    corr
    -0.07
    æĪ¿åľ°
    -0.07
     bezieh
    -0.07
    ÙĪØ®
    -0.07
    tock
    -0.07
     воÑĤ
    -0.06
    _BINDING
    -0.06
    ìłĦ문
    -0.06
    WN
    -0.06
    宸
    -0.06
    POSITIVE LOGITS
    éijij
    0.07
    antai
    0.07
    èĥ½çļĦ
    0.07
    èĥ½åĴĮ
    0.07
    å±±ä¹ĭ
    0.06
    åĬŁäºİ
    0.06
    以赴
    0.06
    ordova
    0.06
    ç±³ç²ī
    0.06
    With
    0.06
    Activations Density 0.009%

    No Known Activations