© 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. 10518
    Prev
    Next
    INDEX
    Explanations

    control stability analysis

    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
    æ³ķå®ļ代表
    -0.08
    à¸Ľà¸¥
    -0.08
    verages
    -0.07
    oule
    -0.07
    æ³ķ人代表
    -0.07
    dbo
    -0.07
    两æĢ§
    -0.07
     stranded
    -0.07
    èķĥ
    -0.07
    /perl
    -0.07
    POSITIVE LOGITS
     tunes
    0.09
     Tun
    0.08
     stability
    0.08
     tuning
    0.08
     Control
    0.08
    æݧåĪ¶
    0.08
     controller
    0.08
    /security
    0.08
    antil
    0.07
    bruck
    0.07
    Activations Density 0.006%

    No Known Activations