© 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. 9055
    Prev
    Next
    INDEX
    Explanations

    functional units or components

    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
    pte
    -0.08
    ercul
    -0.08
     pembukaan
    -0.08
    缸åħ³è¦ģæ±Ĥ
    -0.08
     pote
    -0.08
    交éĢļè¿Ŀæ³ķè¡Į为
    -0.07
    .gradle
    -0.07
    ÙĦÙĤاء
    -0.07
    ebro
    -0.07
    gré
    -0.07
    POSITIVE LOGITS
     housed
    0.10
    è´Łè´£
    0.10
    è´Łè´£å¯¹
    0.10
     responsible
    0.09
    สà¹Īวà¸Ļ
    0.09
     tasked
    0.08
     subsystem
    0.08
     components
    0.08
    åIJĦåı¸
    0.08
    è¿IJä½ľ
    0.08
    Activations Density 0.199%

    No Known Activations