© 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. 17697
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    åħĭå°Ķ
    -0.08
    gara
    -0.08
     دÙģ
    -0.07
    èµ¢äºĨ
    -0.07
    è¡£é£Ł
    -0.07
    åįķ人
    -0.07
    riz
    -0.07
    duk
    -0.07
    лк
    -0.07
    è´¹æŶ
    -0.07
    POSITIVE LOGITS
    äºĮæľ¬
    0.07
    isl
    0.07
    -around
    0.07
    èĥ½å¤ŁæĽ´å¥½åľ°
    0.07
    åĪĨå·¦åı³
    0.07
    usercontent
    0.07
    驻马
    0.07
    .omg
    0.07
    ä¿ł
    0.07
    ered
    0.06
    Activations Density 0.013%

    No Known Activations