© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48379
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts

    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
    ravi
    -0.07
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    prus
    -0.07
    schul
    -0.07
    unami
    -0.07
    riles
    -0.07
    alde
    -0.07
    æľ¬æ¥¼
    -0.06
    rato
    -0.06
    ibraries
    -0.06
    POSITIVE LOGITS
    stub
    0.07
    åĴĮå¹³
    0.07
    å¥Ķèµ°
    0.07
    asty
    0.07
    assist
    0.07
    employ
    0.06
    ç«ł
    0.06
    åĬ©æĶ»
    0.06
    æķĪèĥ½
    0.06
    ä¹ĭä¸į
    0.06
    Activations Density 0.002%

    No Known Activations