© 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. 26477
    Prev
    Next
    INDEX
    Explanations

    spatial extent or coverage

    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
    amus
    -0.07
    heu
    -0.07
    emplace
    -0.07
    èī²åĪĹ
    -0.07
    Ĥ¹
    -0.07
    ×ķ×¢
    -0.07
    å½ĵçĿĢ
    -0.07
     separately
    -0.07
    igl
    -0.07
    ä¸įæĶ¾
    -0.07
    POSITIVE LOGITS
    广度
    0.16
    å¹¿æ³ĽçļĦ
    0.15
    -wide
    0.15
    éģįåıĬ
    0.15
    è¦ĨçĽĸ
    0.15
     coverage
    0.15
    è¦ĨçĽĸéĿ¢
    0.15
    æī©å¤§
    0.15
    å¹¿æ³Ľ
    0.14
    èĮĥåĽ´å¹¿
    0.14
    Activations Density 0.267%

    No Known Activations