© 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. 64152
    Prev
    Next
    INDEX
    Explanations

    configurations achieved

    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
    çļĦéĤ£ä¸ª
    -0.06
    oule
    -0.06
    nk
    -0.06
    -t
    -0.06
     –
    -0.06
    åģĩ
    -0.06
     n
    -0.06
     tack
    -0.06
    大éĩı
    -0.06
     ng
    -0.06
    POSITIVE LOGITS
    è¿ĻåĽĽä¸ª
    0.13
    è¿ĻåĽĽ
    0.13
    åĽĽä¸ª
    0.11
     ÑĩеÑĤÑĭÑĢеÑħ
    0.11
    è¿Ļåĩł
    0.10
    åĽĽä¸ªäºº
    0.10
    åĽĽæĿ¡
    0.10
     four
    0.10
     keempat
    0.10
    åĽĽäºº
    0.10
    Activations Density 0.130%

    No Known Activations