© 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. 48275
    Prev
    Next
    INDEX
    Explanations

    ">" symbols or code delimiters

    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
    ptica
    -0.08
    ÑģÑģо
    -0.07
    çļĦçŀ¬éĹ´
    -0.07
     pate
    -0.07
    баÑĤ
    -0.07
    交çļĦ
    -0.07
    åįĥçĻ¾
    -0.07
    éģŃåĪ°äºĨ
    -0.07
    bruch
    -0.07
    port
    -0.06
    POSITIVE LOGITS
    缴åĪ°
    0.10
     until
    0.10
    缴èĩ³
    0.09
    until
    0.09
    ãģ¾ãģ§
    0.08
     até
    0.07
     Until
    0.07
     hasta
    0.07
     eventual
    0.07
     fend
    0.07
    Activations Density 0.013%

    No Known Activations