© 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. 55956
    Prev
    Next
    INDEX
    Explanations

    second derivative of

    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
    оÑģÑĤа
    -0.08
    å¥Ī
    -0.07
    otec
    -0.07
    Hu
    -0.07
    人äºĭ
    -0.07
    .cor
    -0.07
    棺
    -0.06
    еÑģÑĤв
    -0.06
    尺度
    -0.06
    untu
    -0.06
    POSITIVE LOGITS
    tart
    0.07
    Äįo
    0.07
    CIF
    0.07
     изве
    0.07
    æĸ¹æ³ķåıĬ
    0.07
    ÑĢно
    0.07
    Ùħبر
    0.07
    åĤį
    0.07
     Moro
    0.07
     Fam
    0.07
    Activations Density 0.035%

    No Known Activations