© 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. 17787
    Prev
    Next
    INDEX
    Explanations

    ordinal/cardinal numbers and months

    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
    bf
    -0.06
    u
    -0.06
    bu
    -0.05
     comparison
    -0.05
    ষà§įà¦ł
    -0.05
     Associ
    -0.05
    ä¹ĭåĪĹ
    -0.05
    æ¯Ķä¸įä¸Ĭ
    -0.05
     Migr
    -0.05
     Comparison
    -0.05
    POSITIVE LOGITS
    ammer
    0.06
    kira
    0.06
    emat
    0.06
    à¥ĩल
    0.06
     presidenta
    0.06
     =>$
    0.06
    å¼ĥ
    0.06
    -Israel
    0.06
    æĿIJæĸĻä¸İ
    0.05
    å¤ļç±³
    0.05
    Activations Density 0.032%

    No Known Activations