© 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. 18743
    Prev
    Next
    INDEX
    Explanations

    many years

    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
    arra
    -0.06
    è°ĵä¹ĭ
    -0.06
     Ze
    -0.05
    eu
    -0.05
    awk
    -0.05
    çļĦ人æĿ¥è¯´
    -0.05
    çļĦä¸Ģå®ļ
    -0.05
    Ze
    -0.05
     Zimmerman
    -0.05
    åıijæĶ¾
    -0.05
    POSITIVE LOGITS
    ailable
    0.06
     frac
    0.06
     terce
    0.05
    çļĦé¦ĸ
    0.05
    atis
    0.05
    anko
    0.05
    isting
    0.05
    é¦ĸéķ¿
    0.05
     subdiv
    0.05
    Marca
    0.05
    Activations Density 0.003%

    No Known Activations