© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18622
    Prev
    Next
    INDEX
    Explanations

    outfits, requirements, networking, essay

    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
    wig
    -0.06
    é¨İ士
    -0.06
    charge
    -0.06
    fertig
    -0.06
     پشت
    -0.06
    اÙħÙĬØ©
    -0.05
    à¸ī
    -0.05
    ç¥
    -0.05
     aforementioned
    -0.05
    amar
    -0.05
    POSITIVE LOGITS
    龸
    0.05
    çļĦç»ıéªĮ
    0.05
     –
    0.05
    æݥ轨
    0.05
    odon
    0.05
    èĢĮè¨Ģ
    0.05
    çļĦé¦ĸ
    0.05
    æ¡Īä¸Ń
    0.05
    ikas
    0.05
    ught
    0.05
    Activations Density 0.005%

    No Known Activations