© 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. 19431
    Prev
    Next
    INDEX
    Explanations

    star-crossed romance

    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
    æł¼å°Ķ
    -0.06
     Balance
    -0.05
     banda
    -0.05
    æľĢæĸ°
    -0.05
    adian
    -0.05
     balance
    -0.05
     bit
    -0.05
     DIA
    -0.05
    å¼Ģåıijåĩº
    -0.05
    ÙĪÙī
    -0.05
    POSITIVE LOGITS
     separation
    0.06
    cis
    0.06
     sépar
    0.05
    Separ
    0.05
    Cele
    0.05
    æīij
    0.05
    æ°ijæĶ¿å±Ģ
    0.05
    بÛĮÙĨ
    0.05
    Separated
    0.05
    fony
    0.05
    Activations Density 0.007%

    No Known Activations