© 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. 26315
    Prev
    Next
    INDEX
    Explanations

    recycling and related words

    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
    è°ĥåĪ°
    -0.08
    欲
    -0.07
    ä¸įå®ī
    -0.07
    ä¸į稳
    -0.07
    ä¸įè°ĥ
    -0.07
    躲
    -0.07
    -anchor
    -0.07
    ulun
    -0.07
    çªģ
    -0.07
    umon
    -0.07
    POSITIVE LOGITS
     reuse
    0.16
     reused
    0.14
    reuse
    0.14
    åĨįåĪ©çĶ¨
    0.12
    Reuse
    0.12
     reusable
    0.12
    åĽŀæĶ¶
    0.12
     recycling
    0.12
    循çݯåĪ©çĶ¨
    0.11
     recycle
    0.11
    Activations Density 0.057%

    No Known Activations