© 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. 50384
    Prev
    Next
    INDEX
    Explanations

    figures 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
    alit
    -0.08
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    çĴ§
    -0.06
    çĦķ
    -0.06
    ulas
    -0.06
    iat
    -0.06
    é»Ħæ²Ļ
    -0.06
    quio
    -0.06
    å½ĵåħ¶
    -0.06
    æľīæĪij
    -0.06
    POSITIVE LOGITS
    ouv
    0.08
    鼨ä¸Ń
    0.07
    Title
    0.07
    venues
    0.07
    inqu
    0.07
    май
    0.07
    AMED
    0.07
    agini
    0.07
    å±¥è¡ĮåIJĪåIJĮ
    0.07
    çĶµè·¯åĽ¾
    0.07
    Activations Density 0.052%

    No Known Activations