© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21048
    Prev
    Next
    INDEX
    Explanations

    human rights organisations and activists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oglio
    -0.07
    eração
    -0.06
    umos
    -0.06
    entra
    -0.06
    æĤ£èĢħçļĦ
    -0.06
     Healthy
    -0.06
     Tentang
    -0.06
    ãĤĪãģĹ
    -0.06
     takim
    -0.06
    vere
    -0.06
    POSITIVE LOGITS
     systematically
    0.05
    NEL
    0.05
    oms
    0.05
    eneg
    0.05
     Freed
    0.05
    ascript
    0.05
    ['_
    0.05
    دÙħات
    0.05
     spot
    0.05
    ased
    0.05
    Activations Density 0.006%

    No Known Activations