© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30257
    Prev
    Next
    INDEX
    Explanations

    schema definitions and code structures

    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
    er
    -0.13
    à§įস
    -0.09
    overe
    -0.08
    ectores
    -0.08
    à§įত
    -0.08
    opsy
    -0.08
    etahui
    -0.08
    好å¤ĦçļĦ
    -0.07
    porn
    -0.07
    à§įন
    -0.07
    POSITIVE LOGITS
    0.09
    bies
    0.08
    edly
    0.07
    lec
    0.07
    ständig
    0.07
    sWith
    0.07
    ë¦¬ê³ł
    0.07
    t
    0.07
    /AFP
    0.07
    avigator
    0.07
    Activations Density 0.001%

    No Known Activations