© 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. 8233
    Prev
    Next
    INDEX
    Explanations

    patents and articles

    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
    olumn
    -0.08
    à¹Īวà¸ĩ
    -0.08
    åħ¶å®ĥåªĴä½ĵ
    -0.08
    å·¥åķĨ注åĨĮåı·
    -0.08
    BOSE
    -0.07
    اپ
    -0.07
    วà¸ģ
    -0.07
    estr
    -0.07
    _photos
    -0.07
    imap
    -0.07
    POSITIVE LOGITS
    è¡Įäºij
    0.07
     aforementioned
    0.07
    ä¸Ĭè¿°
    0.07
    ä¸ĢèĦī
    0.07
    ä¸Ĭè¿°äºĭå®ŀ
    0.07
    alkan
    0.06
    çļĦè¿Ļä¸Ģ
    0.06
    è¿ijè·Ŀ离
    0.06
     above
    0.06
    каÑĢбо
    0.06
    Activations Density 0.020%

    No Known Activations