© 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. 13702
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending in s or es

    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
    ļ
    -0.08
    nicz
    -0.07
    ¼
    -0.07
    Ļ
    -0.07
    bnb
    -0.07
    ripp
    -0.07
    ÙĤاÙĨ
    -0.06
    oy
    -0.06
    lyn
    -0.06
    umenten
    -0.06
    POSITIVE LOGITS
     beiden
    0.08
    WG
    0.08
    urge
    0.07
    ÑĪнÑı
    0.07
    elig
    0.07
    æĸĩæѦ
    0.07
    ä¸įåIJĮ
    0.07
    ursa
    0.07
    å§Ķ
    0.07
    AGA
    0.07
    Activations Density 0.416%

    No Known Activations