© 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. 26055
    Prev
    Next
    INDEX
    Explanations

    matching, match, matched

    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
    iminal
    -0.07
    nict
    -0.07
    anita
    -0.07
    zat
    -0.06
    巾帼
    -0.06
    NodeType
    -0.06
    èģ¯
    -0.06
    åĥļ
    -0.06
    ë©Ģ
    -0.06
     guad
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.14
     matching
    0.13
    match
    0.13
     match
    0.13
     matched
    0.12
     Matching
    0.12
    åĮ¹éħįçļĦ
    0.12
    matching
    0.11
    -match
    0.11
     Match
    0.11
    Activations Density 0.413%

    No Known Activations