© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    surveillance, ISO, efficient

    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
    åĿŀ
    -0.07
     ấy
    -0.06
    emer
    -0.06
    ág
    -0.06
    æĿ¥è¯´æĺ¯
    -0.06
    ini
    -0.05
    anger
    -0.05
    .,
    -0.05
    æ§ĺ
    -0.05
    mart
    -0.05
    POSITIVE LOGITS
    ONOM
    0.08
    顾åIJįæĢĿä¹ī
    0.08
    ioc
    0.08
    uchia
    0.08
    onav
    0.08
    åĪĻå°Ĩ
    0.08
     enfin
    0.08
    isex
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
     schlieÃŁlich
    0.08
    Activations Density 0.010%

    No Known Activations