© 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. 65454
    Prev
    Next
    INDEX
    Explanations

    reading, restore, line, cannabis, sleep, wanted, protocol

    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
     гÑĢÑı
    -0.09
    mata
    -0.08
     hers
    -0.08
    èĮ²
    -0.08
     Grosso
    -0.08
    åħ¹
    -0.08
    åıijçĶŁçļĦäºĭæĥħ
    -0.08
    欣
    -0.07
    ulia
    -0.07
    اذ
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    vinc
    0.06
     boc
    0.06
    èIJ¨æĸ¯
    0.06
    ÑģÑĤÑĮ
    0.06
     hay
    0.05
    æĥ³ä¸įåĪ°
    0.05
    hal
    0.05
     ove
    0.05
    åĽłä¸ºè¿Ļ
    0.05
    Activations Density 0.040%

    No Known Activations