© 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. 31058
    Prev
    Next
    INDEX
    Explanations

    .h after lua

    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
    _collection
    -0.08
    ä¸ªå·¥ä½ľæĹ¥åĨħ
    -0.07
    ollection
    -0.07
    ILD
    -0.07
    -collection
    -0.07
    ubo
    -0.07
     Enterprises
    -0.07
    irit
    -0.07
    Collections
    -0.07
    æĪijçŁ¥éģĵäºĨ
    -0.07
    POSITIVE LOGITS
    èĶĵ
    0.07
    bdb
    0.07
    çĪ±æĥľ
    0.07
    æ£ĺ
    0.06
    éļ¾æ±Ĥ
    0.06
     pee
    0.06
    bum
    0.06
    بت
    0.06
    dae
    0.06
    جÙĬ
    0.06
    Activations Density 0.041%

    No Known Activations