© 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. 55922
    Prev
    Next
    INDEX
    Explanations

    sub- prefixes

    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
    enius
    -0.08
    èĥĮéĿł
    -0.08
    aliz
    -0.07
    ÏĢη
    -0.07
    enticated
    -0.07
    elper
    -0.07
    ildo
    -0.07
    åĪ©äºŀ
    -0.07
    hiri
    -0.07
    éĻ¤äºĨåľ¨
    -0.07
    POSITIVE LOGITS
     thereof
    0.09
     of
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.07
    åī²
    0.07
     subset
    0.07
    åŃIJ
    0.07
     Reit
    0.06
    roda
    0.06
    èĬĿ
    0.06
     davon
    0.06
    Activations Density 0.020%

    No Known Activations