© 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. 16797
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code syntax

    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
    enzi
    -0.08
    entu
    -0.07
    chez
    -0.07
    粧
    -0.07
    ent
    -0.07
    æĬĬåŃ©åŃIJ
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
     GENERATED
    -0.07
     Gerhard
    -0.07
    äºĶ粮液
    -0.06
    POSITIVE LOGITS
    rium
    0.07
    leigh
    0.07
    ityEngine
    0.07
    ipmap
    0.07
    aci
    0.07
    _longitude
    0.06
    ysin
    0.06
     avs
    0.06
    çĪ±äºº
    0.06
    wal
    0.06
    Activations Density 0.002%

    No Known Activations