© 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. 42460
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and variables

    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
    ctest
    -0.08
    alan
    -0.07
    anch
    -0.07
    सर
    -0.07
    assi
    -0.07
    =post
    -0.07
    æĹħæ¸¸çĽ®çļĦåľ°
    -0.07
    lotte
    -0.07
    ough
    -0.07
    å³
    -0.07
    POSITIVE LOGITS
    便å°Ĩ
    0.07
    Âł
    0.07
    çIJ¥çıĢ
    0.06
     dab
    0.06
    åıĪå°Ĩ
    0.06
    éĩijèī²
    0.06
    ä¹Łä¸įçŁ¥
    0.06
    çŁ¥æĥħ
    0.06
    éĩijæĸ¯
    0.06
    åĪ©æĸ¯
    0.06
    Activations Density 0.003%

    No Known Activations