© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19508
    Prev
    Next
    INDEX
    Explanations

    Django

    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
    ↵
    -0.07
     y
    -0.05
    acy
    -0.05
    ilde
    -0.05
    ['
    -0.05
    nit
    -0.05
    ↵↵
    -0.05
     se
    -0.05
    iction
    -0.05
    ex
    -0.05
    POSITIVE LOGITS
    zinho
    0.08
    inée
    0.07
    voli
    0.07
     konst
    0.07
    iems
    0.07
    ستÙĨ
    0.07
    è¾¾åĨħ
    0.07
    ابÙĦ
    0.07
    hargaan
    0.07
    teca
    0.07
    Activations Density 0.005%

    No Known Activations