© 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. 24284
    Prev
    Next
    INDEX
    Explanations

    Billy Peyton

    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
    ä¹Ĺ
    -0.08
    hq
    -0.08
    eturn
    -0.07
    ê°
    -0.06
    ango
    -0.06
    Gem
    -0.06
    ä¹Łä¸įåĨį
    -0.06
    vip
    -0.06
    ä¹ŁæľīäºĽ
    -0.06
    两侧çļĦ
    -0.06
    POSITIVE LOGITS
     mau
    0.07
    WORD
    0.07
    DataContract
    0.07
     Worcester
    0.07
    nets
    0.07
    以任ä½ķ
    0.06
    é¦ĸéĥ½
    0.06
    inou
    0.06
    åĨĴ
    0.06
    åħ¶ä»ĸæĸ¹å¼ı
    0.06
    Activations Density 0.012%

    No Known Activations