© 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. 55946
    Prev
    Next
    INDEX
    Explanations

    DNA extraction

    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
    esen
    -0.08
     relief
    -0.07
    åĸ·æ°´
    -0.07
    å¸ĥç½®
    -0.07
    å¨ĺ
    -0.07
     sprink
    -0.07
     Relief
    -0.07
    åı¯ä»¥çľĭ
    -0.06
    çĪ¹çĪ¹
    -0.06
     spraying
    -0.06
    POSITIVE LOGITS
    纯åĮĸ
    0.10
    è¯ķåīĤçĽĴ
    0.09
     extracts
    0.09
    -kit
    0.09
    åĪ¶å¤ĩ
    0.09
     extracted
    0.08
    agate
    0.08
    æıIJåıĸ
    0.08
     harvested
    0.08
     extract
    0.08
    Activations Density 0.034%

    No Known Activations