© 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. 17813
    Prev
    Next
    INDEX
    Explanations

    specific indoor spaces

    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
    imb
    -0.05
    å¿¿
    -0.05
     maintenance
    -0.05
    abus
    -0.05
    åµĮ
    -0.05
     faveur
    -0.05
    çĪ¬å±±
    -0.05
    åĴª
    -0.05
    鸳
    -0.05
    -off
    -0.05
    POSITIVE LOGITS
    为ä¹ĭ
    0.06
    çŁ¥åħ¶
    0.06
    da
    0.06
    ุà¹īà¸ĩ
    0.06
    æѤåīįçļĦ
    0.06
    éf
    0.06
    nin
    0.06
    éĿ¢æĹł
    0.06
    èĩªçŁ¥
    0.05
    æīĵèµ¢
    0.05
    Activations Density 0.002%

    No Known Activations