© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    `Index`, `Avg`, `Naming`

    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
     appunto
    -0.09
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.09
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    DMETHOD
    -0.07
    egah
    -0.07
    aros
    -0.07
    antha
    -0.07
    .pretty
    -0.07
    emet
    -0.06
    ç»ıèIJ¥çºłçº·
    -0.06
    POSITIVE LOGITS
    ùm
    0.07
    .named
    0.07
    æĦ§
    0.07
    HELL
    0.06
    ingly
    0.06
    èijĹ
    0.06
    çŀİ
    0.06
    æĸ°åħī
    0.06
    ide
    0.06
    azen
    0.06
    Activations Density 0.350%

    No Known Activations