© 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. 38516
    Prev
    Next
    INDEX
    Explanations

    company 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
    orni
    -0.07
     Nug
    -0.06
    .microsoft
    -0.06
     basal
    -0.06
    baz
    -0.06
    æĹłå°½çļĦ
    -0.06
    ÙĪاء
    -0.06
     Microsoft
    -0.06
    ä¸įåħ¥
    -0.06
    Microsoft
    -0.06
    POSITIVE LOGITS
    天åħĥ
    0.08
     menda
    0.08
    æĺİä¿¡
    0.07
    _vlog
    0.07
    Ĥ
    0.07
    åħĭç½Ĺ
    0.07
    è£ħ饰设计
    0.07
    intern
    0.07
     Montr
    0.07
    ugas
    0.07
    Activations Density 0.458%

    No Known Activations