© 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. 19758
    Prev
    Next
    INDEX
    Explanations

    codes, types, RC4, encryption

    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
     gesta
    -0.07
    ewise
    -0.06
     ulang
    -0.06
     dÃło
    -0.06
    åįģ足
    -0.06
    ÃģP
    -0.06
    åįģ足çļĦ
    -0.06
    çĽİçĦ¶
    -0.06
    åĦ¿çļĦ
    -0.06
    åĩºèĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
    ÙĬØ©
    0.08
    ive
    0.08
    ed
    0.07
    ìĿĺ
    0.07
    çļĦæł¸å¿ĥ
    0.06
    ãģ®
    0.06
    place
    0.06
    printf
    0.06
    ÙĬات
    0.06
    го
    0.05
    Activations Density 0.028%

    No Known Activations