© 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. 4094
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    âĺĨâĺĨ
    -0.06
     mong
    -0.06
     Hers
    -0.06
    è¾¹çķĮ
    -0.06
     bean
    -0.06
     vul
    -0.06
     ATS
    -0.06
    let
    -0.06
    å¹³
    -0.06
    co
    -0.06
    POSITIVE LOGITS
    icit
    0.09
    æĤ¨çļĦä½įç½®
    0.09
    ombang
    0.09
    алÑĮÑı
    0.08
    DED
    0.08
    yms
    0.08
    ¥
    0.08
    éī¢
    0.08
    alitas
    0.08
    меÑģÑĤи
    0.08
    Activations Density 0.010%

    No Known Activations