© 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. 7478
    Prev
    Next
    INDEX
    Explanations

    state of being after 'is' or 'was'

    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
     vorba
    -0.08
    amac
    -0.08
    irable
    -0.08
    eluk
    -0.08
     terecht
    -0.08
    æµ·æ·ĺ
    -0.08
    prend
    -0.08
     lyk
    -0.08
    çļĦ人ä¼ļ
    -0.08
    reen
    -0.08
    POSITIVE LOGITS
     ...
    0.07
    ä»£æĽ¿
    0.06
    vents
    0.06
    ...
    0.06
     indeed
    0.06
     probably
    0.06
    åģĩå¦Ĥ
    0.06
    па
    0.06
    éĪ
    0.06
    0.05
    Activations Density 1.632%

    No Known Activations