© 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. 20409
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     indef
    -0.06
    anat
    -0.06
     Bale
    -0.06
    éķ¿æľŁä½¿çĶ¨
    -0.06
    ECTION
    -0.05
     séqu
    -0.05
     asc
    -0.05
    Ñıн
    -0.05
    ãģ£ãģ¦ãģĹãģ¾ãģ£ãģŁ
    -0.05
    rect
    -0.05
    POSITIVE LOGITS
    ç½ijç«Ļåľ°åĽ¾
    0.06
     cola
    0.05
    arr
    0.05
    åħĨ
    0.05
    “
    0.05
    éĿĴæ¢ħ
    0.05
     distress
    0.05
    èģļåĬĽ
    0.05
    `${
    0.05
    ardon
    0.05
    Activations Density 0.002%

    No Known Activations