© 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. 8282
    Prev
    Next
    INDEX
    Explanations

    radiolysis, damage, biological impact, localized energy

    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
    flix
    -0.08
     hugged
    -0.07
     trading
    -0.07
    Outlet
    -0.07
     Trading
    -0.07
     relu
    -0.07
    使èĩªå·±çļĦ
    -0.07
     ajar
    -0.07
    oren
    -0.07
    HCM
    -0.07
    POSITIVE LOGITS
     bystand
    0.10
     localized
    0.09
     surrounding
    0.08
     deposited
    0.08
     nearby
    0.08
    æĴŃ
    0.08
    éĻĦè¿ij
    0.08
    /ion
    0.07
    åij¨åĽ´
    0.07
    localized
    0.07
    Activations Density 0.028%

    No Known Activations