© 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. 23756
    Prev
    Next
    INDEX
    Explanations

    `else if`

    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
    Ú¯ÙĪ
    -0.06
    ç¾½
    -0.06
    eo
    -0.06
    eluk
    -0.06
    ic
    -0.06
    arya
    -0.06
    宿
    -0.06
    embra
    -0.06
    r
    -0.06
    dim
    -0.06
    POSITIVE LOGITS
    æĦıæĥ³
    0.08
    rollers
    0.07
    Occurred
    0.07
    é»ĺé»ĺçļĦ
    0.07
    ä¸įåħ¥
    0.07
    ÑĢика
    0.07
    ynos
    0.07
    ä¸įé½IJ
    0.07
    ffin
    0.07
    ä¸įåıĤåĬł
    0.07
    Activations Density 0.013%

    No Known Activations