© 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. 28412
    Prev
    Next
    INDEX
    Explanations

    biotinyl, sin, NSData, opencv, data, number

    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
    ent
    -0.06
     Liter
    -0.06
    urop
    -0.06
    esty
    -0.06
    åħ¶äºĮ
    -0.06
    ette
    -0.06
    åĪ«è¯´
    -0.06
    ås
    -0.06
    æĿĤ
    -0.06
    ow
    -0.06
    POSITIVE LOGITS
    awan
    0.08
    isman
    0.08
     nbytes
    0.07
    ayakan
    0.07
    èľĴ
    0.07
    ãģĿãĤį
    0.07
    ÙĪÙĬب
    0.07
    é«ĺçŃīéĻ¢æł¡
    0.07
    stdarg
    0.07
    ulty
    0.07
    Activations Density 0.003%

    No Known Activations