© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26827
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

    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
    adona
    -0.07
    edList
    -0.07
    icle
    -0.07
     лом
    -0.06
     Torrent
    -0.06
    è·Ŀ
    -0.06
    здÑĢа
    -0.06
    å´İ
    -0.06
    åħ¶å®ĥåªĴä½ĵ
    -0.06
    æĺĵ
    -0.06
    POSITIVE LOGITS
    æĪijçļĦçľĭæ³ķ
    0.07
    tto
    0.07
    mime
    0.07
    çĶ±ä¹Ļæĸ¹
    0.07
    undu
    0.07
    ê°ĢìĻĢ
    0.07
    dene
    0.06
    ystate
    0.06
    ħ
    0.06
     be
    0.06
    Activations Density 0.010%

    No Known Activations