© 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. 50546
    Prev
    Next
    INDEX
    Explanations

    either or

    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
    èĻ½çĦ¶è¯´
    -0.08
    èĨĬ
    -0.08
    bsd
    -0.08
     zwar
    -0.08
    although
    -0.08
    leid
    -0.08
    aidu
    -0.07
    allas
    -0.07
    ignored
    -0.07
    llib
    -0.07
    POSITIVE LOGITS
     depending
    0.23
    åıĸåĨ³äºİ
    0.18
    depending
    0.18
     Depending
    0.17
    Depending
    0.17
     dependendo
    0.16
     dependiendo
    0.14
    æł¹æį®ä¸įåIJĮçļĦ
    0.13
     depends
    0.12
     завиÑģимоÑģÑĤи
    0.11
    Activations Density 0.059%

    No Known Activations