© 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. 1724
    Prev
    Next
    INDEX
    Explanations

    tensor math and programming examples

    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
    æ¯ĶåĪ©
    -0.08
    onsin
    -0.08
     prezi
    -0.07
     kil
    -0.07
     vents
    -0.07
     baud
    -0.06
    ç¾ļç¾Ĭ
    -0.06
    åŃ£åIJİ
    -0.06
     TECN
    -0.06
     ता
    -0.06
    POSITIVE LOGITS
    ä»İ头
    0.07
    éĴ©
    0.07
    .getPath
    0.07
    incoming
    0.07
     interceptor
    0.07
     propri
    0.07
     incoming
    0.07
    åĭ¾
    0.06
    stick
    0.06
    åĥµå°¸
    0.06
    Activations Density 0.014%

    No Known Activations