© 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. 45814
    Prev
    Next
    INDEX
    Explanations

    code ending in parenthesis or brace

    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
    ATHER
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    çıĪ
    -0.08
    reiber
    -0.08
    jong
    -0.08
    gear
    -0.08
    æĪĸå¤ļ个
    -0.08
    lai
    -0.08
    ä¼ĺçĶŁ
    -0.08
    ffici
    -0.08
    POSITIVE LOGITS
    åĬłä¸Ĭ
    0.07
     plus
    0.07
     Meanwhile
    0.07
    èĢĮå·²
    0.06
    ande
    0.06
    plus
    0.06
    åıĪå¦Ĥ
    0.06
     meanwhile
    0.06
    æĸ¯
    0.06
    åı¦å¤ĸ
    0.06
    Activations Density 0.013%

    No Known Activations