© 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. 19488
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating context

    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
    éĶŃ
    -0.07
    vious
    -0.06
    opsy
    -0.06
    åŀ¢
    -0.06
    eus
    -0.06
     []).
    -0.05
    ä¸Ńè¶ħ
    -0.05
     genu
    -0.05
    é»ijåıij
    -0.05
    ertiary
    -0.05
    POSITIVE LOGITS
    第ä¸Ģä½į
    0.05
     dij
    0.05
     harsh
    0.05
    оÑģÑĮ
    0.05
    éĺ²æŃ¢
    0.05
    orz
    0.05
    ibra
    0.05
     ÙĪØ£Ùģ
    0.05
     potent
    0.05
     tune
    0.05
    Activations Density 0.002%

    No Known Activations