© 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. 22194
    Prev
    Next
    INDEX
    Explanations

    adverb followed by adjective/noun

    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
    ORO
    -0.06
    uk
    -0.06
     رÙĪÙĨ
    -0.06
    sonian
    -0.06
    iru
    -0.06
    ipas
    -0.06
    ienti
    -0.06
    ä¸įè´¥
    -0.06
    oidal
    -0.06
    pled
    -0.05
    POSITIVE LOGITS
     unh
    0.05
     degree
    0.05
     amount
    0.05
     dosage
    0.05
    说æĿ¥
    0.05
     kali
    0.05
     ÙĨÚ©
    0.05
    RESS
    0.05
     amounts
    0.05
     rassegna
    0.05
    Activations Density 0.228%

    No Known Activations