© 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. 50835
    Prev
    Next
    INDEX
    Explanations

    A followed by colon

    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
    à¸ķร
    -0.07
    eta
    -0.06
     ter
    -0.06
    Õ¡Õ¾
    -0.06
    und
    -0.06
     artwork
    -0.06
     Davidson
    -0.06
     writeln
    -0.06
    ா
    -0.06
    jes
    -0.06
    POSITIVE LOGITS
    æī©å±ķèµĦæĸĻ
    0.08
    indow
    0.08
    isman
    0.07
    票æķ°
    0.07
    ĩ
    0.07
    è¿Ļ让æĪij
    0.07
    驳
    0.07
    bersome
    0.07
    agri
    0.07
    è·»
    0.07
    Activations Density 0.038%

    No Known Activations