© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15132
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols, names like Welch Diamond

    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
    vw
    -0.07
    aat
    -0.06
    box
    -0.06
    è¿ĩèĬĤ
    -0.06
    io
    -0.06
    ogg
    -0.06
    less
    -0.06
    rapper
    -0.06
    app
    -0.05
    fun
    -0.05
    POSITIVE LOGITS
    <|box_end|>
    0.09
     Nazar
    0.08
    æĿİè½»
    0.08
    iston
    0.08
    emani
    0.07
    æķ£åıij
    0.07
    ×ķ×ķת
    0.07
     certif
    0.07
    שר
    0.07
    ãĥĩãĤ£ãĤª
    0.07
    Activations Density 0.117%

    No Known Activations