© 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. 46228
    Prev
    Next
    INDEX
    Explanations

    castle instance

    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
    æĿ¿å¼ı
    -0.07
    /name
    -0.07
    cq
    -0.06
     Huss
    -0.06
    athi
    -0.06
    plom
    -0.06
    ãĥ«ãĥī
    -0.06
     Gutenberg
    -0.06
    åį¿
    -0.06
    URE
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.09
    ++.
    0.08
    ãĥĦãĥ¼
    0.08
    otes
    0.07
    æĪĸå°ij
    0.07
    ĥģ
    0.07
    çĬ¯çļĦ
    0.07
    etra
    0.07
    éŁ
    0.07
    quam
    0.07
    Activations Density 0.002%

    No Known Activations