© 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. 21508
    Prev
    Next
    INDEX
    Explanations

    quantifiers or numbers followed by nouns

    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¸ĢåįĬ
    -0.05
    åĽĽäºº
    -0.05
    转
    -0.05
    åıª
    -0.05
     bothering
    -0.05
     parap
    -0.05
    unate
    -0.05
     guarantee
    -0.05
    æĺ¾çľ¼
    -0.05
    лам
    -0.05
    POSITIVE LOGITS
     various
    0.07
    çĹħæĥħåĪĨæŀIJ
    0.06
    fila
    0.06
     Nuit
    0.06
    AGER
    0.06
    elic
    0.06
    ismer
    0.06
    ocz
    0.06
    亿åIJ¨
    0.06
    ERIC
    0.06
    Activations Density 0.073%

    No Known Activations