© 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. 14473
    Prev
    Next
    INDEX
    Explanations

    squared terms

    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
    éĿ¢æľĿ
    -0.07
    åĴĮ帮åĬ©
    -0.07
    esis
    -0.06
    帮åĬ©åĪ«äºº
    -0.06
     dipimpin
    -0.06
    缮çļĦåľ°
    -0.06
    çĹĽå¿«
    -0.06
    roscope
    -0.06
    hop
    -0.06
     ble
    -0.06
    POSITIVE LOGITS
     squared
    0.11
    quared
    0.10
    å¹³æĸ¹
    0.10
    Squared
    0.09
     Squ
    0.09
    ãĥĨãĥ¼
    0.08
    尼奥
    0.08
    _squared
    0.08
    squ
    0.08
    .square
    0.08
    Activations Density 0.040%

    No Known Activations