© 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. 27885
    Prev
    Next
    INDEX
    Explanations

    commercial property, skiing, servers

    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
    çĦ¶å¤§
    -0.08
    /forms
    -0.08
    fst
    -0.07
    京
    -0.07
    æIJº
    -0.07
    encodeURIComponent
    -0.07
    ioso
    -0.07
    çļĦå°ıç¼ĸ
    -0.07
    /Branch
    -0.07
    perto
    -0.07
    POSITIVE LOGITS
    u
    0.08
    or
    0.07
    ãĢģ
    0.06
     downright
    0.06
    t
    0.06
    Âł
    0.06
    É
    0.06
    oley
    0.06
    æĪĸèĢħ
    0.06
    èĢĢçľ¼çļĦ
    0.06
    Activations Density 0.497%

    No Known Activations