© 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. 19301
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    endorf
    -0.07
    addock
    -0.07
    liess
    -0.07
    ner
    -0.07
    erta
    -0.06
    สา
    -0.06
    chand
    -0.06
    orny
    -0.06
    ushi
    -0.06
    æĶ¾åĩº
    -0.06
    POSITIVE LOGITS
    端åĢª
    0.07
    BP
    0.07
    çľī
    0.07
    é¢ĨåħĪçļĦ
    0.07
     rekre
    0.07
    _VARS
    0.07
    hão
    0.06
    IZAR
    0.06
    å¼¹
    0.06
    ax
    0.06
    Activations Density 0.002%

    No Known Activations