© 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. 18275
    Prev
    Next
    INDEX
    Explanations

    specific numbers or prefixes/suffixes

    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
    vero
    -0.08
    建åįİ
    -0.08
    å½İ
    -0.07
     giò
    -0.07
    ë´ī
    -0.07
    Ø´ÙĦ
    -0.07
    åİļçĪ±
    -0.07
    _DIRECTORY
    -0.07
    ÙĨدÙĩ
    -0.07
    inator
    -0.07
    POSITIVE LOGITS
    ardin
    0.07
     vertu
    0.07
     virtue
    0.07
    æĢ§çļĦ
    0.06
    kat
    0.06
     marin
    0.06
    اÙĦÙĬØ©
    0.06
     vir
    0.06
    ä¸ĩèĥ½
    0.06
    हि
    0.06
    Activations Density 0.001%

    No Known Activations