© 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. 15353
    Prev
    Next
    INDEX
    Explanations

    case numbers and citations

    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
    apo
    -0.08
    åıªæĢķ
    -0.08
    ç®ĢåįķçļĦ
    -0.07
    ία
    -0.07
    мÑı
    -0.07
    atable
    -0.07
     opro
    -0.07
    anitize
    -0.06
    笼
    -0.06
    çµIJå±Ģ
    -0.06
    POSITIVE LOGITS
    ..'
    0.08
    `\
    0.07
    `t
    0.07
    風ãģ«
    0.07
     âĸij
    0.07
    æ¯Ķè¾ĥ好çļĦ
    0.07
    araf
    0.07
    '",
    0.06
     lùng
    0.06
     Konz
    0.06
    Activations Density 0.796%

    No Known Activations