© 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. 18568
    Prev
    Next
    INDEX
    Explanations

    bilinear predict

    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
     afterward
    -0.06
    paring
    -0.06
    BS
    -0.06
     afterwards
    -0.05
    ulatory
    -0.05
    izat
    -0.05
     Hors
    -0.05
     sometimes
    -0.05
    amp
    -0.05
    S
    -0.05
    POSITIVE LOGITS
    enheim
    0.07
    yi
    0.06
    ",[
    0.05
    обе
    0.05
    åĴ§
    0.05
    ÙĦÙģÙĬØ©
    0.05
    ÙĪØ¡
    0.05
    -extension
    0.05
     PHI
    0.05
    AdminController
    0.05
    Activations Density 0.027%

    No Known Activations