© 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. 64699
    Prev
    Next
    INDEX
    Explanations

    counting possibilities

    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
    æĬĺ
    -0.08
    追
    -0.08
    avel
    -0.08
    æ»¡åľ°
    -0.07
    伤åı£
    -0.07
    æķĪæŀľæĽ´å¥½
    -0.07
     Blasio
    -0.07
    壹
    -0.07
    leston
    -0.07
    港å¸Ĥ
    -0.07
    POSITIVE LOGITS
    artes
    0.07
     exponentially
    0.07
    unchecked
    0.07
     possibilities
    0.07
     possibile
    0.07
    åħį费注åĨĮ
    0.07
    çļĦåı¯èĥ½
    0.07
    å¼ĢæĶ¾çļĦ
    0.07
     (~(
    0.07
    ç«ĭæĸ¹
    0.07
    Activations Density 0.028%

    No Known Activations