© 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. 56707
    Prev
    Next
    INDEX
    Explanations

    property name | group by | date range | time period | for loop | engine size | YAML import

    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
    entif
    -0.08
    ighted
    -0.08
    aims
    -0.07
    åįģä¸ĢæĿ¡
    -0.07
    Markers
    -0.07
     вÑĢ
    -0.07
    _annotations
    -0.07
    è¦ļ
    -0.06
    iega
    -0.06
    ä¼ģä¸ļä¸ļåĬ¡
    -0.06
    POSITIVE LOGITS
     кÑģÑĤаÑĤи
    0.08
    lander
    0.07
     ÙĩÙĨا
    0.07
    z
    0.07
    ument
    0.07
    wl
    0.06
    Ãĩ
    0.06
    ter
    0.06
    çĶ»å»Ĭ
    0.06
    æľĢ好
    0.06
    Activations Density 0.091%

    No Known Activations