© 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. 39480
    Prev
    Next
    INDEX
    Explanations

    "distance" or "squared"

    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
    aum
    -0.09
    ilog
    -0.09
     Ranh
    -0.09
    åĩºå¸Ńä¼ļè®®
    -0.08
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.08
    úa
    -0.08
    ç»´æĸ¯
    -0.08
     Lô
    -0.08
    åĬłåĭĴ
    -0.08
    pressa
    -0.08
    POSITIVE LOGITS
     distance
    0.08
    etailed
    0.07
     squared
    0.07
     distances
    0.07
    Distance
    0.06
     Distance
    0.06
    0.06
    distance
    0.06
    éģº
    0.06
    è·Ŀ离
    0.06
    Activations Density 0.002%

    No Known Activations