© 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. 19380
    Prev
    Next
    INDEX
    Explanations

    names or technical identifiers

    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
     soon
    -0.07
    é¢ĸ
    -0.06
     bientôt
    -0.06
    ä¸įä¹ħ
    -0.06
    Ñijм
    -0.06
     Ñĩел
    -0.05
    rop
    -0.05
    ake
    -0.05
    çŃī设å¤ĩ
    -0.05
    å¾Īå¿«çļĦ
    -0.05
    POSITIVE LOGITS
    iguez
    0.09
    óg
    0.08
    çŃĭ骨
    0.08
    utore
    0.08
    versi
    0.08
    åıijèĩª
    0.08
    æĵ
    0.08
    еÑģÑĤв
    0.08
    енÑģа
    0.07
    oxel
    0.07
    Activations Density 0.002%

    No Known Activations