© 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. 41703
    Prev
    Next
    INDEX
    Explanations

    numbers and units like meters, years, percent

    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
    天é¾Ļ
    -0.08
     }):
    -0.08
     psa
    -0.07
    utel
    -0.06
     incor
    -0.06
    Wire
    -0.06
    ç¸ģ
    -0.06
     بÙħع
    -0.06
    æ·¡æ·¡
    -0.06
    èµĦæºIJç½ij
    -0.06
    POSITIVE LOGITS
    ï¼ĭ
    0.08
    **–
    0.08
    à¸Ńà¸Ļ
    0.07
     plus
    0.07
    ãĥİãĤ¦
    0.07
    +")
    0.07
    .adv
    0.07
    -plus
    0.07
    æĪijåıªæĥ³
    0.07
    +d
    0.07
    Activations Density 0.169%

    No Known Activations