© 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. 21775
    Prev
    Next
    INDEX
    Explanations

    guy describing people

    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
     je
    -0.06
    æĬķ
    -0.05
     unre
    -0.05
     post
    -0.05
     ot
    -0.05
     ed
    -0.05
     ta
    -0.05
    æļij
    -0.05
     om
    -0.05
    country
    -0.05
    POSITIVE LOGITS
    ebilecek
    0.06
    emplate
    0.06
    acons
    0.06
    vil
    0.06
    gó
    0.06
    çĽĪçĽĪ
    0.06
     pilota
    0.06
    amon
    0.06
    porté
    0.06
    ebile
    0.06
    Activations Density 0.001%

    No Known Activations