© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    numbers and time periods

    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
    姨
    -0.08
    herits
    -0.07
    ohl
    -0.07
    çĽ¸å®¹
    -0.07
    dcc
    -0.07
    Compat
    -0.07
    ÑħÑĢо
    -0.07
    amay
    -0.07
    æĪij社
    -0.07
    :item
    -0.07
    POSITIVE LOGITS
    ecchio
    0.08
     xxx
    0.07
    rodom
    0.06
    缮çļĦ
    0.06
    æľĢåIJİä¸Ģåħ¬éĩĮ
    0.06
    æŁIJçĶ²
    0.06
    _MPI
    0.06
    fant
    0.06
    æłĩ书
    0.06
    ption
    0.06
    Activations Density 0.504%

    No Known Activations