© 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. 40571
    Prev
    Next
    INDEX
    Explanations

    factorial and factory related terms

    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
    à¸ģารà¸ĵà¹Į
    -0.09
    edor
    -0.09
    ளà¯įள
    -0.09
    esh
    -0.09
    é¹Ĭ
    -0.08
    elay
    -0.08
    rafo
    -0.08
    eenth
    -0.08
    åĪ°çļĦ
    -0.08
    iglio
    -0.08
    POSITIVE LOGITS
    -like
    0.07
    ลà¸ļ
    0.07
    ate
    0.07
    ä¸įèĻļ
    0.07
    adat
    0.07
    ä¸Ĭçģ«
    0.06
    loon
    0.06
    adic
    0.06
    rvine
    0.06
    اÙĨ
    0.06
    Activations Density 0.001%

    No Known Activations