© 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. 24546
    Prev
    Next
    INDEX
    Explanations

    balancing forces and equilibrium

    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
    iec
    -0.07
    ptime
    -0.07
    pline
    -0.07
    çī¹åĽ°
    -0.06
    åIJį家
    -0.06
    åŁİ乡å±ħæ°ij
    -0.06
     reper
    -0.06
    OVA
    -0.06
     enke
    -0.06
     conforms
    -0.06
    POSITIVE LOGITS
    平衡
    0.13
     balancing
    0.12
     balance
    0.12
    balance
    0.11
     balances
    0.11
    Balance
    0.10
    Bal
    0.10
     Balance
    0.10
     Bal
    0.09
     balanced
    0.09
    Activations Density 0.004%

    No Known Activations