© 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. 24489
    Prev
    Next
    INDEX
    Explanations

    set methods

    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
    é¹ĥ
    -0.09
    .decorators
    -0.08
    IGA
    -0.08
    orong
    -0.08
    ibun
    -0.08
    ÏĢον
    -0.08
    createView
    -0.08
    çªĿéĩĮ
    -0.08
    ä¸įå¤ļ说
    -0.08
    å®Ŀåħ¸
    -0.08
    POSITIVE LOGITS
     setting
    0.10
    æĶ¹åıĺ
    0.09
     changing
    0.09
     set
    0.09
    设置
    0.08
     Changing
    0.08
    设å®ļ
    0.08
     changed
    0.08
    .Change
    0.08
     Set
    0.08
    Activations Density 0.176%

    No Known Activations