© 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. 38339
    Prev
    Next
    INDEX
    Explanations

    programming and sequence indices

    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
    quil
    -0.07
    å§ĭèĩ³
    -0.07
     Cheney
    -0.07
     bold
    -0.07
    èĥ½åĬĽåıĬ
    -0.06
    åĭĩæ°ĶåĴĮ
    -0.06
    ews
    -0.06
    ebro
    -0.06
    åĪ°æĤ¨
    -0.06
    egen
    -0.06
    POSITIVE LOGITS
     alike
    0.08
    ä¸įåĴĮ
    0.08
    .python
    0.08
    .numpy
    0.07
    γÏĮ
    0.07
    ä¸įåĩºåİ»
    0.07
    inie
    0.07
    usher
    0.07
    ropy
    0.07
    '#
    0.07
    Activations Density 0.004%

    No Known Activations