© 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. 13433
    Prev
    Next
    INDEX
    Explanations

    unicode escape sequences and code comments

    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
    acic
    -0.07
    å¹³åĩ¡çļĦ
    -0.07
    Ľ
    -0.06
    çıĬçıĬ
    -0.06
    ãĥªãĤ¨
    -0.06
    åĿļ
    -0.06
    ç¾²
    -0.06
    åĩ¹åĩ¸
    -0.06
     witnessed
    -0.06
    çļĦæĺ¯
    -0.06
    POSITIVE LOGITS
    زاÙĦ
    0.08
    æħķå°¼
    0.07
    uite
    0.07
    acionais
    0.07
    kho
    0.07
    ",-
    0.07
    abet
    0.07
    åıĤä¸İè¯Ħ论
    0.07
    ooks
    0.07
    ."\
    0.06
    Activations Density 0.043%

    No Known Activations