© 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. 21215
    Prev
    Next
    INDEX
    Explanations

    margin, padding, border

    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
    éĢĤåºĶèĥ½åĬĽ
    -0.06
     forza
    -0.06
    éĻĦ
    -0.06
    æĺı
    -0.06
    angu
    -0.05
    æĬķéĻį
    -0.05
    çļĦçݯå¢ĥä¸ĭ
    -0.05
    ç»ıèIJ¥çĬ¶åĨµ
    -0.05
    éĻĦæľī
    -0.05
     Nuestro
    -0.05
    POSITIVE LOGITS
     Cham
    0.06
    åħĪè¡Į
    0.06
    &m
    0.06
     Poz
    0.05
    اÙĨد
    0.05
    æĸĭ
    0.05
    ZER
    0.05
    空çļĦ
    0.05
    ellos
    0.05
    æŃ£çļĦ
    0.05
    Activations Density 0.027%

    No Known Activations