© 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. 19497
    Prev
    Next
    INDEX
    Explanations

    VR headsets and wearables

    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
    odge
    -0.06
    รุà¸ģ
    -0.06
    à¸ķร
    -0.05
    pos
    -0.05
    éģģ
    -0.05
    undi
    -0.05
     unle
    -0.05
     Protected
    -0.05
    unning
    -0.05
     Exterior
    -0.05
    POSITIVE LOGITS
    æĿŁ
    0.06
    éĩıåĬĽ
    0.06
     hardware
    0.06
    hardware
    0.06
    бли
    0.06
    device
    0.06
     behalf
    0.06
     pacing
    0.05
     device
    0.05
    举
    0.05
    Activations Density 0.024%

    No Known Activations