© 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. 16727
    Prev
    Next
    INDEX
    Explanations

    new versions and changes

    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
    è¶Ĭä½İ
    -0.07
    çĽ¸æľĽ
    -0.07
     usually
    -0.07
    妥妥
    -0.07
    ebet
    -0.06
    ä¸Ģ次åıĪä¸Ģ次
    -0.06
    ykk
    -0.06
     Usually
    -0.06
    йм
    -0.06
    娴
    -0.06
    POSITIVE LOGITS
    æĸ°çļĦ
    0.17
    åħ¨æĸ°çļĦ
    0.15
     revamped
    0.15
    çŃīæĸ°
    0.14
    æ¯Ķ以å¾Ģ
    0.14
     new
    0.13
     redesigned
    0.13
    åīįæīĢæľªæľīçļĦ
    0.13
    æ¯Ķ以åīį
    0.13
     جدÛĮد
    0.12
    Activations Density 0.907%

    No Known Activations