© 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. 63213
    Prev
    Next
    INDEX
    Explanations

    arbitrary [noun]

    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
    iliz
    -0.10
    ÙĤات
    -0.09
    ularity
    -0.09
    ppure
    -0.09
    ilit
    -0.09
    warzys
    -0.09
    agerie
    -0.08
    uvre
    -0.08
    redo
    -0.08
    presso
    -0.08
    POSITIVE LOGITS
    erweise
    0.11
    ly
    0.10
    æĥħåĨµä¸ĭ
    0.09
    ç¨ĭ度
    0.07
    åľ°å°Ĩ
    0.07
    ´
    0.06
    ãģĹãĤĤ
    0.06
    lie
    0.06
    ÅĽÄĩ
    0.06
    ificial
    0.06
    Activations Density 0.005%

    No Known Activations