© 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. 20919
    Prev
    Next
    INDEX
    Explanations

    financial and physiological balance

    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
    łí
    -0.08
    å®ļåŀĭ
    -0.08
    ezz
    -0.08
    èªĺ
    -0.07
    ordes
    -0.07
    ä¸Ģæī¶
    -0.07
    æĮijèµ·
    -0.07
    dex
    -0.07
    icur
    -0.07
    mina
    -0.07
    POSITIVE LOGITS
    平衡
    0.11
     balance
    0.10
    å®ĪæģĴ
    0.10
    æĶ¶æĶ¯
    0.10
     Balance
    0.09
     flows
    0.09
     balances
    0.09
     net
    0.09
    Balance
    0.09
    åĩĢ
    0.08
    Activations Density 0.020%

    No Known Activations