© 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. 62979
    Prev
    Next
    INDEX
    Explanations

    rubyPrototypespecsassrails

    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
     Vietnamese
    -0.07
    é¦ĸå°Ķ
    -0.07
    è¶ĬåįĹ
    -0.07
     Nantes
    -0.07
    çĴŁ
    -0.07
    èļĮ
    -0.07
     viet
    -0.07
    ifax
    -0.07
    rij
    -0.07
     Ches
    -0.07
    POSITIVE LOGITS
    æĪIJéĥ½å¸Ĥ
    0.15
    åľ¨æĪIJéĥ½
    0.15
    æĶĢæŀĿèĬ±
    0.13
    èľĢ
    0.13
    æĪIJéĥ½
    0.13
    绵éĺ³
    0.13
    åĽĽå·Ŀçľģ
    0.13
     Colorado
    0.12
    .SQLite
    0.12
    绵éĺ³å¸Ĥ
    0.12
    Activations Density 1.115%

    No Known Activations