© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    structure of, populations of, variant shown

    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
    缸åħ³æ³ķå¾ĭæ³ķè§Ħ
    -0.07
    azza
    -0.07
    æĽ¾åĽł
    -0.07
    æīĢæıIJä¾ĽçļĦ
    -0.07
    åıĹè¿ĩ
    -0.07
    due
    -0.07
     varsa
    -0.07
     vanwege
    -0.07
    çªģå¦Ĥåħ¶æĿ¥çļĦ
    -0.07
     reciente
    -0.07
    POSITIVE LOGITS
     tersendiri
    0.10
    çŃīä¸Ģç³»åĪĹ
    0.08
    å¦Ĥä¸ĭåĽ¾
    0.08
    并æľĢç»Ī
    0.07
    ä¹ħä¹ĭ
    0.07
    ä¸įå°ıçļĦ
    0.07
    =:
    0.07
    æł¼å¤ĸçļĦ
    0.07
    ä¸įå°ijçļĦ
    0.07
    ().'
    0.07
    Activations Density 0.194%

    No Known Activations