© 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. 30493
    Prev
    Next
    INDEX
    Explanations

    PLoS ONE, IEEE Transactions, Reviews

    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
    λί
    -0.08
    udre
    -0.08
    æĮ¯
    -0.08
    /antlr
    -0.08
    eteria
    -0.08
    lexport
    -0.07
    erta
    -0.07
    udio
    -0.07
    achen
    -0.07
    åıijè¨Ģ稿
    -0.07
    POSITIVE LOGITS
    éĹĬ
    0.09
    鸥
    0.06
    Metro
    0.06
    asaki
    0.06
    *)_
    0.06
    çľīçľ¼
    0.05
    ênh
    0.05
    رص
    0.05
    æĬĢæľ¯åľ¨
    0.05
     Crossing
    0.05
    Activations Density 0.043%

    No Known Activations