© 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. 20825
    Prev
    Next
    INDEX
    Explanations

    helper functions and code internals

    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
    è¶Ĭèµ°è¶Ĭ
    -0.08
    æĺ¯å¥½
    -0.07
    -ie
    -0.07
    onie
    -0.07
    LOCATION
    -0.07
    å¾ĹçĽĬ
    -0.07
    缴æİ¥æĪĸ
    -0.07
    roj
    -0.07
    ÅĦskiej
    -0.07
    asen
    -0.07
    POSITIVE LOGITS
    ingleton
    0.08
    çĶ¨æĿ¥
    0.07
    ¾
    0.07
    å¿Ļ
    0.07
    è¾Ī
    0.07
    åħ¼
    0.07
    itaire
    0.06
    ä»
    0.06
     *–
    0.06
    è½¼
    0.06
    Activations Density 0.016%

    No Known Activations