© 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. 43987
    Prev
    Next
    INDEX
    Explanations

    confirmation of agreement

    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
    æī«
    -0.07
    éĩĪ
    -0.07
    æ¯Ķçħ§
    -0.07
    çķĻä½ı
    -0.06
    Ø·ÙĦ
    -0.06
    _OVERRIDE
    -0.06
    icates
    -0.06
     Rush
    -0.06
    ides
    -0.06
    åĪ°äºº
    -0.06
    POSITIVE LOGITS
    bauer
    0.08
    inni
    0.08
    çļĦ好æĪIJ绩
    0.08
    arring
    0.07
    aland
    0.07
    apper
    0.07
    alter
    0.07
    ulin
    0.07
    olina
    0.07
     floats
    0.07
    Activations Density 0.005%

    No Known Activations