© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    symbols and separators

    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
    еÑĩÑĮ
    -0.08
    -0.07
     dec
    -0.07
     Conserv
    -0.06
    kou
    -0.06
    plevel
    -0.06
    æŦ
    -0.06
     si
    -0.06
    à¸Ńà¸Ļ
    -0.06
     Schwartz
    -0.06
    POSITIVE LOGITS
    .generated
    0.09
    æ¦Ħ
    0.09
    xim
    0.08
    濯
    0.08
     Journ
    0.08
    æł©
    0.08
    å¥½ä¸ľè¥¿
    0.08
    à¤ķारà¥Ģ
    0.08
    æ·Į
    0.08
    erio
    0.08
    Activations Density 0.005%

    No Known Activations