© 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. 61932
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code syntax

    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
    LLU
    -0.08
    IGA
    -0.08
    ozen
    -0.07
    leftright
    -0.07
    iin
    -0.07
    egah
    -0.07
    åłª
    -0.07
    .tight
    -0.07
    Odd
    -0.07
    å¥ĩ
    -0.07
    POSITIVE LOGITS
    èIJ¥
    0.07
     Keh
    0.07
    çĩŁ
    0.06
    åĸĦ
    0.06
    æĪĸä¸İ
    0.06
    robat
    0.06
    uros
    0.06
     marketing
    0.06
    ê¼
    0.06
     McB
    0.06
    Activations Density 0.008%

    No Known Activations