© 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. 28860
    Prev
    Next
    INDEX
    Explanations

    math, programming, names, sqrt

    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
    ELLOW
    -0.07
    icle
    -0.07
     Hi
    -0.06
    èĥ½å¤Łä½¿
    -0.06
    å°Ĩ使
    -0.06
    ä¸įæ¯Ķ
    -0.06
    ellow
    -0.06
    ä»Ĩ
    -0.06
    渺
    -0.06
    对åħ¶ä»ĸ
    -0.06
    POSITIVE LOGITS
    éĩij森
    0.08
    bior
    0.08
    شت
    0.08
    åĩ¯è¿ª
    0.07
    åħ·æľī丰å¯ĮçļĦ
    0.07
    ä¸ĩ象
    0.07
     gấp
    0.07
    -num
    0.07
    Ïĩαν
    0.07
     اÙĦعض
    0.07
    Activations Density 0.004%

    No Known Activations