© 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. 30617
    Prev
    Next
    INDEX
    Explanations

    sports statistics or scores

    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
    uil
    -0.07
    usif
    -0.07
    ebel
    -0.07
     devi
    -0.07
    æĭĩ
    -0.07
     trÆ°Æ¡ng
    -0.07
    夹
    -0.07
    {@
    -0.07
    æIJģ
    -0.07
    社åĮºåį«çĶŁ
    -0.07
    POSITIVE LOGITS
     Rou
    0.07
    unc
    0.07
    æĺİ
    0.07
    unu
    0.07
     Trout
    0.06
    داد
    0.06
    ince
    0.06
     unc
    0.06
    aw
    0.06
     terminal
    0.06
    Activations Density 0.127%

    No Known Activations