© 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. 43106
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables

    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
    riers
    -0.07
    ignano
    -0.06
     Wired
    -0.06
    æĹłæĦ§
    -0.06
    trieve
    -0.06
    amera
    -0.06
    ä¸įå®ļæľŁ
    -0.06
    ä¸įæ¸ħæ¥ļ
    -0.06
    ä¸įä¸Ģ
    -0.06
    ID
    -0.06
    POSITIVE LOGITS
    æ»¡çľ¼
    0.08
    jø
    0.08
    ITAS
    0.07
    å°ıåŃIJ
    0.07
    htub
    0.07
    çIJIJ
    0.07
     corrup
    0.07
    ÙĬÙĪ
    0.07
    ãĥ¼ãĥĦ
    0.07
    æĸĩæĺĮ
    0.07
    Activations Density 0.072%

    No Known Activations