© 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. 61814
    Prev
    Next
    INDEX
    Explanations

    agamiidae genus

    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
    æĻ©
    -0.07
    æ
    -0.06
    累累
    -0.06
     неп
    -0.06
    çݯ
    -0.06
     '
    -0.06
    çļĦ好
    -0.06
    çĶŁæ´»
    -0.06
    æĨĭ
    -0.05
     عاÙħÙĭا
    -0.05
    POSITIVE LOGITS
    åĭ¢
    0.08
    说åĪ°è¿ĻéĩĮ
    0.08
     Guardiola
    0.07
    CALE
    0.07
    schlag
    0.07
    hani
    0.07
    tui
    0.07
    æѦåĻ¨è£ħå¤ĩ
    0.07
    DirectoryName
    0.07
    rag
    0.07
    Activations Density 0.001%

    No Known Activations