© 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. 21860
    Prev
    Next
    INDEX
    Explanations

    numbers and "single"

    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
    æģ¶æĢ§
    -0.07
    dech
    -0.05
    immers
    -0.05
    cean
    -0.05
     inform
    -0.05
    åIJ«çĿĢ
    -0.05
     infos
    -0.05
    Op
    -0.05
     Inform
    -0.05
     Desktop
    -0.05
    POSITIVE LOGITS
    baut
    0.06
    æĸ°åĬłåĿ¡
    0.06
    ério
    0.06
    αÏĥ
    0.06
    _uniform
    0.06
    mek
    0.05
    uniform
    0.05
    Uniform
    0.05
     uniform
    0.05
    annon
    0.05
    Activations Density 0.006%

    No Known Activations