© 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. 61808
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or names

    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
    太ä»ĵ
    -0.06
    éļı
    -0.06
    é«ĺ度çļĦ
    -0.06
    ankan
    -0.06
     Heights
    -0.06
    UGHT
    -0.06
    ook
    -0.06
     ÑĥÑģ
    -0.06
    eed
    -0.06
    è®¤çľŁçłĶ究
    -0.06
    POSITIVE LOGITS
    hofer
    0.09
    缸åħ³æĸĩç«ł
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.08
     Criterion
    0.08
     criter
    0.08
    ãĤĤãģ¡
    0.08
     memberships
    0.08
    membership
    0.08
    igner
    0.08
    ellij
    0.07
    Activations Density 0.008%

    No Known Activations