© 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. 34478
    Prev
    Next
    INDEX
    Explanations

    author initials and names

    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
    irkan
    -0.08
    ulah
    -0.08
    éļĪ
    -0.08
    ITAR
    -0.07
    ä½ľä¸ºä¸Ģ家
    -0.07
    ocaust
    -0.07
    Ä©
    -0.07
    ilah
    -0.07
     gostar
    -0.07
    Ú¯ÛĮ
    -0.07
    POSITIVE LOGITS
    æ·»
    0.07
    宿
    0.07
    åıĪ
    0.06
    åıĪ以
    0.06
    æ±Ĥ羣
    0.06
     et
    0.06
    å¼Ĥ
    0.06
     tam
    0.06
    èį£åįİ
    0.06
     circulating
    0.05
    Activations Density 0.086%

    No Known Activations