© 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. 22207
    Prev
    Next
    INDEX
    Explanations

    state of charge, intake, burden, temperature

    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
    tung
    -0.06
    æĿĥ
    -0.06
     provisional
    -0.06
    å±Ĥ
    -0.05
    θη
    -0.05
    .mail
    -0.05
     аз
    -0.05
    代表æĢ§çļĦ
    -0.05
    stri
    -0.05
     Narod
    -0.05
    POSITIVE LOGITS
    Pressed
    0.06
    ucker
    0.06
     entw
    0.06
    odore
    0.06
     stated
    0.05
    odate
    0.05
     zad
    0.05
    /license
    0.05
    ToOne
    0.05
    occo
    0.05
    Activations Density 0.001%

    No Known Activations