© 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. 47974
    Prev
    Next
    INDEX
    Explanations

    individual

    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
     Sandbox
    -0.08
    .vstack
    -0.07
     Lagu
    -0.06
    æĢ»éĩı
    -0.06
    çĶ
    -0.06
    ffy
    -0.06
    çŃī主è¦ģ
    -0.06
    輸
    -0.06
     Chall
    -0.06
    irsi
    -0.06
    POSITIVE LOGITS
    /single
    0.13
    åѤ
    0.13
    æĪĸå°ı
    0.12
    individ
    0.11
    åѤçĭ¬çļĦ
    0.11
    åѤçĭ¬
    0.11
    åѤç«ĭ
    0.11
     individually
    0.11
    à¹Ģà¸Ķีà¹Īยว
    0.11
     individual
    0.11
    Activations Density 0.058%

    No Known Activations