© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    I get/have/can

    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
    dam
    -0.08
    iel
    -0.07
    Bet
    -0.07
    ä¸ĵçĶ¨çļĦ
    -0.07
     ÙħخصÙĪص
    -0.07
     Cast
    -0.06
     specially
    -0.06
    lisi
    -0.06
    ä¾ĿèµĸæĢ§
    -0.06
    åĮħåIJ«çĿĢ
    -0.06
    POSITIVE LOGITS
    åij¼
    0.07
    ipes
    0.07
    rij
    0.07
    çŀİ
    0.07
    ä¸Ĭè¿°
    0.07
    achten
    0.07
     above
    0.07
    åºı
    0.07
    İ
    0.07
     вÑĭÑĪе
    0.07
    Activations Density 0.033%

    No Known Activations