© 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. 42656
    Prev
    Next
    INDEX
    Explanations

    abbreviations and proper nouns

    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
    æŁı
    -0.08
    olen
    -0.06
    ça
    -0.06
     builtin
    -0.06
    åijĬ
    -0.06
    Built
    -0.06
    èIJ¥æķij
    -0.06
    è´¨
    -0.06
    ZR
    -0.06
    olu
    -0.06
    POSITIVE LOGITS
    åIJĮæľŁçļĦ
    0.08
    sworth
    0.08
    è¿ĻåĽĽä¸ª
    0.08
    deles
    0.08
    æĬĬå®ĥ们
    0.08
    oslav
    0.07
    è¿ĻäºĽä¸ľè¥¿
    0.07
    xad
    0.07
    è¿ĻåĽĽ
    0.07
    è®
    0.07
    Activations Density 0.057%

    No Known Activations