© 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. 19528
    Prev
    Next
    INDEX
    Explanations

    returns information

    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
    ated
    -0.06
    âĢ
    -0.06
    å½±åĵįåĪ°
    -0.05
    ishi
    -0.05
    à¸ŀรà¹īà¸Ńมà¸ģัà¸ļ
    -0.05
    duced
    -0.05
    emento
    -0.05
    shire
    -0.05
    er
    -0.05
    atures
    -0.05
    POSITIVE LOGITS
    æī«ä¸Ģæī«
    0.06
    ήμεÏģα
    0.06
    åĨįæ·»
    0.06
    ewise
    0.06
     taki
    0.05
    urch
    0.05
    åıĪå¦Ĥ
    0.05
    ä»Ĭå¤©åľ¨
    0.05
     prat
    0.05
    åħį
    0.05
    Activations Density 0.004%

    No Known Activations