© 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
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19651
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or code strings

    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
    зом
    -0.05
    enni
    -0.05
    tes
    -0.05
    uma
    -0.05
    yh
    -0.05
    Ñģл
    -0.05
    æµģåĬ¨
    -0.05
    ä¸īåĪĨ
    -0.05
    åľĪåľĪ
    -0.05
    ula
    -0.05
    POSITIVE LOGITS
    èĥģ
    0.06
    wai
    0.06
    ί
    0.06
    课çļĦ
    0.05
    práv
    0.05
    Reducer
    0.05
    паÑĤи
    0.05
     Poli
    0.05
    æĭ½
    0.05
    确认åIJİ
    0.05
    Activations Density 0.004%

    No Known Activations