© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18704
    Prev
    Next
    INDEX
    Explanations

    @if, if, then, else, endif

    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
    Realm
    -0.06
    :host
    -0.05
    emma
    -0.05
    iams
    -0.05
    æ°Ľ
    -0.05
    ensburg
    -0.05
     conci
    -0.05
    =localhost
    -0.05
    åĴļ
    -0.05
    ehan
    -0.05
    POSITIVE LOGITS
    pell
    0.06
    stop
    0.05
    vier
    0.05
    ños
    0.05
    bol
    0.05
    éĤ£ä»ĸ
    0.05
    å¾ĢéĩĮ
    0.05
     Swim
    0.05
     than
    0.05
    é¡¹çĽ®çļĦ建设
    0.05
    Activations Density 0.023%

    No Known Activations