© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    Act, Green, Programming, Lesser, Rights, Arts, SID, Escape followed by Tribunal, Interface, Committee, General, Commission, Council, Display, Utils

    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
     L
    -0.07
    abora
    -0.07
    даÑĤ
    -0.06
    æŀ¢
    -0.06
    缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.06
    æĹĭ
    -0.06
    /
    -0.06
    lessly
    -0.06
    æĢ»æ¯Ķ
    -0.06
    *".
    -0.06
    POSITIVE LOGITS
    tlement
    0.07
    çļĦéĩįè¦ģåĨħ容
    0.07
    metatable
    0.07
    ergen
    0.07
    asher
    0.07
    apist
    0.07
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    0.07
     Reifen
    0.07
    ,ep
    0.07
    jis
    0.07
    Activations Density 0.006%

    No Known Activations