© 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. 17588
    Prev
    Next
    INDEX
    Explanations

    terms defined by "called"

    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
     Leverkus
    -0.08
    пÑĤо
    -0.08
    itatif
    -0.08
    ·
    -0.08
    íĬ¼
    -0.08
    _defs
    -0.08
    artet
    -0.08
    volve
    -0.08
    Õµ
    -0.08
    åħĭåĪ©
    -0.08
    POSITIVE LOGITS
    称为
    0.25
    åı«åģļ
    0.24
    被称为
    0.22
    ç§°ä½ľ
    0.21
     called
    0.21
    称ä¹ĭ为
    0.20
    稱çĤº
    0.19
    åı«
    0.18
     termed
    0.18
    called
    0.18
    Activations Density 0.451%

    No Known Activations