© 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. 7922
    Prev
    Next
    INDEX
    Explanations

    multiples of 2 or 3

    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
    IANA
    -0.08
    indra
    -0.08
    ingan
    -0.08
    è°ļ
    -0.08
    ä¹IJçļĦ
    -0.08
    edan
    -0.07
    æ§Ľ
    -0.07
    urator
    -0.07
    rength
    -0.07
    LEY
    -0.07
    POSITIVE LOGITS
     former
    0.07
    ÙĬات
    0.07
    俱åħ¨
    0.06
    å¼ķ
    0.06
    天ä¸Ģ
    0.06
    Former
    0.06
    å¹½
    0.06
     EVERY
    0.06
    çijľ
    0.06
    à°¦à±į
    0.06
    Activations Density 0.007%

    No Known Activations