© 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. 18462
    Prev
    Next
    INDEX
    Explanations

    raft

    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
    fico
    -0.06
    åĤĢåĦ¡
    -0.05
    æĢ§åıĬ
    -0.05
    gl
    -0.05
     sl
    -0.05
    Ø°ÙĬØ©
    -0.05
    åıĬåIJĦ
    -0.05
    ephy
    -0.05
    奴婢
    -0.05
    åIJĦåľ°çļĦ
    -0.05
    POSITIVE LOGITS
     kalinya
    0.06
    stackpath
    0.06
     pursuit
    0.05
    apon
    0.05
    chenk
    0.05
    imper
    0.05
    缴
    0.05
    аниÑĨ
    0.05
    etje
    0.05
    OBO
    0.05
    Activations Density 0.095%

    No Known Activations