© 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. 8007
    Prev
    Next
    INDEX
    Explanations

    shipping container

    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
    abstract
    -0.07
     Abstract
    -0.07
     abstract
    -0.07
    æĬ½è±¡
    -0.07
    çĴĥ
    -0.07
    .abstract
    -0.07
    centes
    -0.07
     patr
    -0.07
    .gc
    -0.07
    ä¸į论
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.13
    åħ¼ä»»
    0.12
    åħ¼ãģŃ
    0.12
    çĶ¨ä½ľ
    0.11
    åħ¼åħ·
    0.10
    ä¸įèĥ½ä½ľä¸º
    0.10
    -turned
    0.10
    åı¯ä»¥ä½ľä¸º
    0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    æĹ¢æĺ¯
    0.09
    Activations Density 0.266%

    No Known Activations