© 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. 60935
    Prev
    Next
    INDEX
    Explanations

    let me show

    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
    ãĥĹ
    -0.07
    _orders
    -0.07
    ifi
    -0.07
    åħ¶æīĢ
    -0.06
    女
    -0.06
    orld
    -0.06
    æľīæľº
    -0.06
    æīĢå¤Ħ
    -0.06
    Ñĥж
    -0.06
    ASSERT
    -0.06
    POSITIVE LOGITS
    esar
    0.08
    omba
    0.08
    HexString
    0.07
    åIJĦä½į家éķ¿
    0.07
    CellValue
    0.07
    oot
    0.07
    å³¥
    0.07
    çľĭé½IJ
    0.07
    ë©ĺ
    0.07
    dings
    0.07
    Activations Density 0.001%

    No Known Activations