© 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. 64237
    Prev
    Next
    INDEX
    Explanations

    special characters and code elements

    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
    çļĦæ°Ķæ°Ľ
    -0.07
    缴èĩ³
    -0.07
    æ¢
    -0.07
    ÏĦαÏĤ
    -0.07
     Bat
    -0.06
    缴åĪ°
    -0.06
    æĬ
    -0.06
     Corm
    -0.06
    bauer
    -0.06
    URY
    -0.06
    POSITIVE LOGITS
    ÑģÑĤоÑĢа
    0.08
    象
    0.08
    é»Ķ
    0.07
    rog
    0.07
    egni
    0.07
    å¼łåħĪçĶŁ
    0.07
    édi
    0.07
    édia
    0.07
    izin
    0.07
    edian
    0.07
    Activations Density 0.007%

    No Known Activations