© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19719
    Prev
    Next
    INDEX
    Explanations

    scoring or present in film

    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
    robe
    -0.06
    èĢħä¹Ł
    -0.05
    azer
    -0.05
    件
    -0.05
    æĩ¿
    -0.05
    ennem
    -0.05
    heus
    -0.05
    éļıå¿ĥ
    -0.05
    ennie
    -0.05
     onto
    -0.05
    POSITIVE LOGITS
    amour
    0.06
    letal
    0.06
     inaccur
    0.05
    kea
    0.05
    æľīæĸĻ
    0.05
    ierer
    0.05
    exercice
    0.05
    etal
    0.05
    undi
    0.05
    ×ĵ×Ļ
    0.05
    Activations Density 0.125%

    No Known Activations