© 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. 19554
    Prev
    Next
    INDEX
    Explanations

    reconstruction of missing data

    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
     descending
    -0.05
    ยà¹Īà¸Ńย
    -0.05
    à¹Ģà¸Ľà¸£
    -0.05
     tally
    -0.05
     flattened
    -0.05
     dissect
    -0.05
    åıĺæĽ´åīį
    -0.05
    è¾±
    -0.05
     crit
    -0.05
    èĭ¦çļĦ
    -0.05
    POSITIVE LOGITS
     missing
    0.07
     reconstruction
    0.07
     Reconstruction
    0.07
    _missing
    0.07
    缺失
    0.07
     Missing
    0.07
    Missing
    0.06
    ulihan
    0.06
    åĢį
    0.06
    ansion
    0.06
    Activations Density 0.020%

    No Known Activations