© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21228
    Prev
    Next
    INDEX
    Explanations

    programming syntax

    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
    çĦ¶
    -0.06
     przep
    -0.05
    iol
    -0.05
    åŃ£èĬĤæĢ§
    -0.05
    plain
    -0.05
    chim
    -0.05
    çĥŃéŨæݨèįIJ
    -0.05
    çļĦçĭĢæ³ģ
    -0.05
    asin
    -0.05
    flt
    -0.05
    POSITIVE LOGITS
    lement
    0.05
    æݨ
    0.05
    åįĴ
    0.05
    ç²¾
    0.05
    enburg
    0.05
     expl
    0.05
    abar
    0.05
    anger
    0.05
     ens
    0.05
    A
    0.05
    Activations Density 0.146%

    No Known Activations