© 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. 18328
    Prev
    Next
    INDEX
    Explanations

    wind power and turbines

    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
     att
    -0.06
    oved
    -0.06
    ifest
    -0.05
    wach
    -0.05
    auj
    -0.05
    ounce
    -0.05
    imbang
    -0.05
    alle
    -0.05
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    -0.05
    allel
    -0.05
    POSITIVE LOGITS
    oriously
    0.07
    ujuan
    0.07
    hout
    0.06
    ìį¨
    0.06
    ro
    0.06
    uhan
    0.06
    خاب
    0.06
    gäng
    0.06
    sky
    0.06
     ÐļÑĢаÑģи
    0.06
    Activations Density 0.007%

    No Known Activations