© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19403
    Prev
    Next
    INDEX
    Explanations

    World Trade Center

    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
    ä¸ĭä¸Ģ次
    -0.06
    ç´ĭ
    -0.06
    hoot
    -0.06
    èĮ´
    -0.06
    edBy
    -0.06
    éľ²å¤´
    -0.06
    åħ·ä½ĵåĪĨæŀIJ
    -0.06
    .OUT
    -0.05
    uiten
    -0.05
     tien
    -0.05
    POSITIVE LOGITS
    agg
    0.05
    å§Ķ
    0.05
    æģĭ
    0.05
    éķľ
    0.05
     impaired
    0.05
    Ùħر
    0.05
     Kuta
    0.05
    åŀĤ
    0.05
    cie
    0.05
    اÙĨÙĩ
    0.05
    Activations Density 0.007%

    No Known Activations