© 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. 46196
    Prev
    Next
    INDEX
    Explanations

    proper nouns from various languages

    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
    �
    -0.07
    -0.07
     chant
    -0.06
    ↵
    -0.06
    -0.06
    ä»İ严
    -0.06
     ode
    -0.06
    -0.06
     unik
    -0.05
    ��
    -0.05
    POSITIVE LOGITS
    jala
    0.09
    ianza
    0.09
    leness
    0.08
     determ
    0.08
    راÙĤÙĬ
    0.08
    anyag
    0.08
    æĹłéĹ»
    0.08
     ÐľÐ°ÑĤеÑĢи
    0.08
    дÑĮми
    0.08
    _resolver
    0.08
    Activations Density 0.045%

    No Known Activations