© 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. 31349
    Prev
    Next
    INDEX
    Explanations

    correspondence or mapping

    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
    OutputStream
    -0.07
    urlencode
    -0.07
    åıĪåı¯
    -0.07
    彤
    -0.07
    å°ı鹿
    -0.07
    igent
    -0.06
    DIR
    -0.06
    æĬ±
    -0.06
    Mur
    -0.06
    æĹ¥ä»İ
    -0.06
    POSITIVE LOGITS
     corresponding
    0.14
    缸åºĶçļĦ
    0.13
    缸åºĶ
    0.13
    对åºĶçļĦ
    0.12
    对åºĶ
    0.11
     entsprechende
    0.11
     correspondant
    0.11
     Correspond
    0.11
     entsprechenden
    0.11
    缸æĩī
    0.10
    Activations Density 0.056%

    No Known Activations