© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    organization, group, or alliance

    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
    俱ä¹IJéĥ¨
    -0.08
    mals
    -0.08
    ening
    -0.07
    å¸Ĥåħ¬å®īå±Ģ
    -0.07
    OrDefault
    -0.07
    ened
    -0.07
    æ·Ĩ
    -0.07
    tti
    -0.06
    åĽ¢éĺŁåįıä½ľ
    -0.06
    ä¸įåģľçļĦ
    -0.06
    POSITIVE LOGITS
    æĪIJåijĺçļĦ
    0.10
    ฯ
    0.10
    ignet
    0.09
    æĪIJåijĺ
    0.09
    wide
    0.08
    æĪIJç«ĭäºİ
    0.08
    -member
    0.08
    °
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    RARY
    0.08
    Activations Density 0.205%

    No Known Activations