© 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. 55947
    Prev
    Next
    INDEX
    Explanations

    palindromic sequences and math

    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
    离å¼Ģ
    -0.07
    ubi
    -0.07
    è¿ľç¦»
    -0.07
     Tres
    -0.07
    esor
    -0.07
    该åĨħ容
    -0.07
     away
    -0.07
    hyl
    -0.07
    èĢĺ
    -0.07
    tres
    -0.07
    POSITIVE LOGITS
    .modified
    0.07
    åı¥åı¥
    0.06
    abic
    0.06
    _zeros
    0.06
     ì§
    0.06
    CORD
    0.06
    é¦ĸéĥ¨
    0.06
    ارÙĬØ©
    0.06
    æļ®
    0.06
    neu
    0.06
    Activations Density 0.001%

    No Known Activations