© 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. 62567
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by 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
    èĥĮå½±
    -0.07
    Ø·Ùģ
    -0.06
    INET
    -0.06
    -out
    -0.06
    èįł
    -0.06
    ä¸įæŃ¢
    -0.06
    åıĤèĢĥ
    -0.06
    ارÛĮ
    -0.06
    outu
    -0.06
    åıĬ以ä¸ĭ
    -0.06
    POSITIVE LOGITS
    åĪĩå®ŀå¢ŀ强
    0.08
    æĢ»ç½²
    0.08
    urz
    0.07
    ickle
    0.07
    thur
    0.07
    裳
    0.07
     вла
    0.07
    itech
    0.07
    积æŀģç»Ħç»ĩ
    0.07
    {i
    0.07
    Activations Density 0.017%

    No Known Activations