© 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. 11210
    Prev
    Next
    INDEX
    Explanations

    downward trend or movement

    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
     uplifting
    -0.09
     uplift
    -0.08
     resurrect
    -0.08
    åįĩ
    -0.08
     ups
    -0.08
    æıIJåįĩ
    -0.08
    温æļĸåĴĮ
    -0.07
     resurrection
    -0.07
    çļĦæıIJåįĩ
    -0.07
     boosting
    -0.07
    POSITIVE LOGITS
    down
    0.16
    éĻįåĪ°
    0.16
    éĻį温
    0.16
    -down
    0.15
    DOWN
    0.14
    éĻįèĩ³
    0.14
     down
    0.13
    以éĻįä½İ
    0.13
    ä¸ĭæĿ¥äºĨ
    0.13
     Down
    0.13
    Activations Density 0.479%

    No Known Activations