© 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. 8468
    Prev
    Next
    INDEX
    Explanations

    special materials and components

    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
    两项
    -0.07
    nade
    -0.07
    niest
    -0.07
    æģĥ
    -0.07
    æľīä¸ĭåĪĹ
    -0.07
    ائÙĤ
    -0.06
    çļĦ主è¦ģåĨħ容
    -0.06
    æī
    -0.06
    æĥ³çĶ¨
    -0.06
    راد
    -0.06
    POSITIVE LOGITS
    éħį以
    0.08
    ç²¾å¿ĥ
    0.08
     avulla
    0.08
     carefully
    0.08
     optional
    0.08
     tailored
    0.07
    éħįåIJĪ
    0.07
     properly
    0.07
     sayesinde
    0.07
    éħįä¸Ĭ
    0.07
    Activations Density 0.081%

    No Known Activations