© 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. 43090
    Prev
    Next
    INDEX
    Explanations

    specified or given

    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
    åIJ«
    -0.07
    ablo
    -0.06
    .WriteString
    -0.06
    ometro
    -0.06
    幡
    -0.06
    ugin
    -0.06
    xac
    -0.06
    ))))
    -0.06
    æĮ¯åįİ
    -0.06
    æĪIJåIJį
    -0.06
    POSITIVE LOGITS
     specified
    0.15
     given
    0.15
    æīĢ
    0.13
    æĮĩå®ļçļĦ
    0.13
    given
    0.13
    ä½łæīĢ
    0.13
    specified
    0.12
    ç»Ļå®ļ
    0.12
    æĪij们æīĢ
    0.12
     chosen
    0.12
    Activations Density 0.375%

    No Known Activations