© 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. 21398
    Prev
    Next
    INDEX
    Explanations

    percentages in parentheses

    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
     lo
    -0.05
    affer
    -0.05
     osc
    -0.05
    ı
    -0.05
    ª
    -0.05
     vá
    -0.05
     volt
    -0.05
    æľĢéģ©
    -0.05
    areth
    -0.05
    spo
    -0.05
    POSITIVE LOGITS
    ãģİ
    0.07
    åĨįè§ģ
    0.06
     Borsa
    0.06
    urias
    0.06
    dff
    0.06
    äºĮ度
    0.06
    åħµåĽ¢
    0.05
    à¸Ĺà¹Īà¸Ńà¸ĩ
    0.05
    ç¹°
    0.05
    büro
    0.05
    Activations Density 0.004%

    No Known Activations