© 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. 21591
    Prev
    Next
    INDEX
    Explanations

    housing developments and properties

    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
    临æŶ
    -0.06
    zzi
    -0.06
    é¢Ħç®Ĺ
    -0.05
    秣åĢŁ
    -0.05
    ÑıÑĤ
    -0.05
     workspace
    -0.05
    æİ¥åľ°
    -0.05
     makeshift
    -0.05
    æľ¨æĿIJ
    -0.05
    çĸĨ
    -0.05
    POSITIVE LOGITS
    모
    0.06
    åĽŀ头
    0.06
    trin
    0.06
    ä¸īæľŁ
    0.06
    ë°ĺ
    0.06
     ÐĴодо
    0.06
     designer
    0.06
    indsight
    0.06
     society
    0.06
    ÏĥÏį
    0.06
    Activations Density 0.071%

    No Known Activations