© 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. 27688
    Prev
    Next
    INDEX
    Explanations

    Vice President

    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
    zelfde
    -0.09
    ertz
    -0.08
    ä¸ĩåį·
    -0.08
    à¸ģำà¹Ģà¸Ļิà¸Ķ
    -0.08
    erness
    -0.08
    สà¹Į
    -0.08
    źdz
    -0.08
     berdua
    -0.07
    åħĭèIJ¨æĸ¯
    -0.07
    ombine
    -0.07
    POSITIVE LOGITS
    -looking
    0.08
    Į
    0.07
    orld
    0.07
    ãģĦãģĪãģ°
    0.07
    ınd
    0.07
    agir
    0.07
    escu
    0.07
    CTION
    0.07
    aries
    0.07
    (er
    0.07
    Activations Density 0.012%

    No Known Activations