© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2588
    Prev
    Next
    INDEX
    Explanations

    name or structure introduction

    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
    plica
    -0.07
    berge
    -0.07
    eiro
    -0.07
    rtl
    -0.07
    è¤
    -0.07
    ÒIJ
    -0.06
    ona
    -0.06
    æĺ¯å¦Ĥä½ķ
    -0.06
    å·Ŀ
    -0.06
     Bol
    -0.06
    POSITIVE LOGITS
    новÑĮ
    0.07
    é¢ł
    0.07
    大头
    0.07
    ÑģлÑĮ
    0.07
    æī¿æı½
    0.07
    åĺĪ
    0.06
    igy
    0.06
    .Reverse
    0.06
    ieved
    0.06
    IndexOf
    0.06
    Activations Density 0.001%

    No Known Activations