© 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. 19888
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and calculations

    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
    dÃ¼ÄŁ
    -0.06
    sel
    -0.05
    éĿ¢åŃIJ
    -0.05
    ingly
    -0.05
    ä¸ĢèĪ¬çļĦ
    -0.05
    åĦ¿
    -0.05
    ä¸įæĺ¯å¾Ī
    -0.05
    延
    -0.05
    åĽ¾çīĩåĴĮ
    -0.05
    å¸ĥé²ģ
    -0.05
    POSITIVE LOGITS
    ocz
    0.07
    aumento
    0.06
    aminer
    0.06
     major
    0.06
     bleed
    0.06
    ERA
    0.05
     Herren
    0.05
    uite
    0.05
    ä¸įæī¿æĭħä»»ä½ķ
    0.05
     disadvantage
    0.05
    Activations Density 0.296%

    No Known Activations