© 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. 9883
    Prev
    Next
    INDEX
    Explanations

    numbers separated by commas or 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
     ((!
    -0.08
    zaam
    -0.08
    çīº
    -0.08
    æİ¥ä¸ĭ
    -0.08
    两边çļĦ
    -0.08
    åĩĽ
    -0.07
     Trento
    -0.07
     zasi
    -0.07
    èĻļå¿ĥ
    -0.07
    peon
    -0.07
    POSITIVE LOGITS
     random
    0.09
    ä¹±çļĦ
    0.09
    ä¹±
    0.09
    random
    0.09
    _random
    0.08
    .random
    0.08
     Random
    0.08
     randomness
    0.08
    éļıæľº
    0.08
    åİŁå§ĭ
    0.08
    Activations Density 0.014%

    No Known Activations