© 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. 18849
    Prev
    Next
    INDEX
    Explanations

    Chinese dynasties and names

    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
    RARY
    -0.11
    lds
    -0.09
    ////////////////////////////////////////////////////////////////////////
    -0.09
    bish
    -0.08
    ftime
    -0.08
    adie
    -0.08
    ////////////////////////////////////////////////////////////
    -0.08
    OnError
    -0.08
    æ§ĥ
    -0.08
    hec
    -0.08
    POSITIVE LOGITS
    eny
    0.08
    eviÄĩ
    0.08
     ráo
    0.07
    ê»ĺ
    0.07
    horn
    0.07
    çģŃ亡
    0.07
    غÙĩ
    0.06
     bì
    0.06
    çģŃ
    0.06
    à¸Ļà¹īำ
    0.06
    Activations Density 0.006%

    No Known Activations