© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    UFC, Henry, Fitzgerald, Speedo, degrowth

    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
    erland
    -0.07
    erk
    -0.07
    elay
    -0.07
    ÙĤا
    -0.06
    lange
    -0.06
    ؤÙĦ
    -0.06
    æĪĸèĢħæĺ¯
    -0.06
     pending
    -0.06
    Ñħодом
    -0.06
    ãģ»
    -0.06
    POSITIVE LOGITS
    VIRTUAL
    0.08
    ombe
    0.07
    ç»´åħĭ
    0.06
    ÏĦιά
    0.06
     Tit
    0.06
    æľĢç»ĪåıĹçĽĬ
    0.06
    .offsetHeight
    0.06
    ãĤ¸ãĥ¥ãĥ¼ãĥ«
    0.06
    Ìģ
    0.06
    .jetbrains
    0.06
    Activations Density 0.008%

    No Known Activations