© 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. 51549
    Prev
    Next
    INDEX
    Explanations

    caption and figures

    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
    -0.08
    eliz
    -0.08
    à§įষ
    -0.07
    èĢIJ
    -0.07
    红èĮ¶
    -0.06
    ifa
    -0.06
    oper
    -0.06
    ене
    -0.06
    urable
    -0.06
    综åIJĪåĪĨæŀIJ
    -0.06
    POSITIVE LOGITS
    ehr
    0.08
    avion
    0.08
    山人海
    0.08
    èĢ³
    0.07
    arb
    0.07
    å§Ĭ妹
    0.07
    èĪŀæĽ²
    0.07
    æĮĿ
    0.07
    åľ¨ä¸Ģ次
    0.07
    issage
    0.07
    Activations Density 0.023%

    No Known Activations