© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 19634
    Prev
    Next
    INDEX
    Explanations

    The presence of numbers, mathematical operations, and variables

    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
    _inc
    -0.06
    θÎŃ
    -0.05
     constituent
    -0.05
    onan
    -0.05
    castle
    -0.05
    ί
    -0.05
    ä¸ĢæĹ¦åĩºçݰ
    -0.05
    èįł
    -0.05
    æĹłå¿Į
    -0.05
     concerns
    -0.05
    POSITIVE LOGITS
    çļĦ確
    0.06
    wai
    0.06
    èĨĢ
    0.05
     drauf
    0.05
    å«Į
    0.05
    irro
    0.05
    —you
    0.05
     BOTH
    0.05
    СÐļÐIJ
    0.05
    mys
    0.05
    Activations Density 0.003%

    No Known Activations