© 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. 62007
    Prev
    Next
    INDEX
    Explanations

    match and similarity

    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
    angan
    -0.07
    æĶ¯æŁ±
    -0.07
    ught
    -0.06
    reon
    -0.06
    ä¸įå®ļæľŁ
    -0.06
    é£İåı£
    -0.06
    èŀº
    -0.06
    ordinated
    -0.06
    åĩĢ
    -0.06
    æĸ°æ°Ķ象
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.14
    -match
    0.12
    _match
    0.12
     matching
    0.12
     match
    0.12
    match
    0.12
    åĮ¹éħįçļĦ
    0.11
    Match
    0.11
    .match
    0.11
     Matching
    0.11
    Activations Density 0.137%

    No Known Activations