© 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. 11500
    Prev
    Next
    INDEX
    Explanations

    legal citation suffix

    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
    à°¡à°¿
    -0.07
    ãĢħ
    -0.07
    ÑĢÑĭз
    -0.07
    venth
    -0.07
    å¿ĥè·³
    -0.07
    .compareTo
    -0.07
    æĢ§éĹ®é¢ĺ
    -0.06
    é¹ħ
    -0.06
    dest
    -0.06
    minster
    -0.06
    POSITIVE LOGITS
    é¦ĸèµŀ
    0.07
     Trin
    0.07
    å°Ħæīĭ
    0.07
    sche
    0.07
    åĬĽ
    0.07
    æ¸ī
    0.06
    izon
    0.06
     Reload
    0.06
    á»ĩt
    0.06
    asury
    0.06
    Activations Density 0.001%

    No Known Activations